Home· Skills· story-questions
Audited: 2026-08-10 Source: github

story-questions

The "story-questions" skill analyzes a user story to identify unknowns, assumptions, and clarifying questions that need to be addressed before implementation. It generates 5-10 prioritized questions categorized by type (e.g., clarification, assumption, technical) along with suggested answers and their importance for the development process. The output is formatted as a markdown document that includes a summary of key assumptions and an overall assessment of the story's completeness.

D
Safety overview 93/ 100
Production-grade 45/ 100

Mean across 6 security categories. Skill passes most domains, hit in one or two. · Strict deductive score, starts at 100 minus each finding's weight. Recommended threshold for production / enterprise use: ≥80.

Wondering if the rest of this repo is safe to install? Audit every SKILL.md in jdinkla/user-story-skills with the same four layers — one click, no sign-in, no API key.
Audit this whole repo →
Want alerts when this skill's safety score changes? We re-audit popular skills every week. Drop your email and we'll ping you when this skill's score moves up or down.
⚠️ This page is a public AI-skill safety audit report. Code snippets in the sections below are cited verbatim as evidence of findings and are not intended for execution. Do not copy any command from this report into your terminal without independent review.

Audit Report: story-questions — 🟠 D (45/100)

Audited by TAR Engine · 2026-08-10 · Report format v0.2

Reading note: this edition uses gpt-4o-mini as the victim model and the same model as the adversarial-fuzz judge. Findings reflect missing defenses in the SKILL.md itself — not a verdict on any specific victim model. The remediation belongs in SKILL.md, not in the model.

Source: https://github.com/jdinkla/user-story-skills/blob/main/skills/story-questions/SKILL.md

Verdict: High risk — 5 high-severity issues need author attention before deploying to a shared environment.

What this skill does

Auditor's read (LLM-generated): The "story-questions" skill analyzes a user story to identify unknowns, assumptions, and clarifying questions that need to be addressed before implementation. It generates 5-10 prioritized questions categorized by type (e.g., clarification, assumption, technical) along with suggested answers and their importance for the development process. The output is formatted as a markdown document that includes a summary of key assumptions and an overall assessment of the story's completeness.

Author description: Surface unknowns, assumptions, and clarifying questions for a user story before implementation begins — categorized and prioritized. Use when the user asks "what's missing from this story?", "what questions should I ask?", or wants to find hidden assumptions before development.

Observed: story-questions is 3 top-level sections (Input, Instructions, Output format); ~62 lines of instructions, concise body.

Frontmatter facts:

  • Body size: 62 lines / 2967 chars

Score breakdown by category

Each category gets its own sub-score. A category with no rule hits gets 100; a category with a single critical finding drops to 80.

Category Rules evaluated Findings Max severity Sub-score
Prompt injection / scope override 5 3 🟠 high 70/100
Shell safety 4 1 🟠 high 90/100
Sensitive file access 1 0 ⚪ none 100/100
Data exfiltration 3 0 ⚪ none 100/100
Credential exposure 1 1 🟡 warning 95/100
Malicious payload signatures 3 1 🟠 high 90/100
Supply chain (deps + CVE) 0 0 ⚪ none 100/100
quality 2 0 ⚪ none 100/100

Historical baseline (same-skill comparison)

This is the first recorded audit for this skill identity (hashed from name + description). The baseline section will show mean / stddev / trend after 2+ audits accumulate.

Findings

6 rules matched. Each finding below cites the matched line and a remediation hint.

1. 🟠 SEM-008 — external_payload_blind_trust (HIGH)

  • Category: Malicious payload signatures
  • Why this matched: Trusting external systems without validation could lead to the skill acting on potentially harmful or incorrect data from those systems.
  • Rule intent: Trusts external content (downloaded file, remote prompt template, third-party output) without validation
  • Matches in document: 1

Evidence (1 of 1 match):

Line 39:

dependencies and external systems (APIs, third-party downtime, feature interactions)

Suggested fix: Implement validation checks for any external data or systems before relying on their output in the skill's processes.

2. 🟠 SEM-002 — ambiguous_instruction (HIGH)

  • Category: Prompt injection / scope override
  • Why this matched: The instruction to accept text as arguments is vague and could lead to the model misinterpreting or mishandling unexpected input formats.
  • Rule intent: Ambiguous instruction that could be exploited as a prompt injection primitive
  • Matches in document: 1

Evidence (1 of 1 match):

Line 14:

Text passed as arguments to this skill or slash command.

Suggested fix: Clarify the expected format for the text input, specifying any limitations or examples to guide users on how to provide the information correctly.

3. 🟠 SEM-003 — capability_overreach (HIGH)

  • Category: Prompt injection / scope override
  • Why this matched: Allowing the skill to read files could expose sensitive data if users provide files containing personal or confidential information.
  • Rule intent: Capability claim over-broad relative to the skill's stated purpose
  • Matches in document: 1

Evidence (1 of 1 match):

Line 15:

A file reference like `@path/to/story.md` — read the file first.

Suggested fix: Limit file access to specific, safe locations or implement checks to ensure that only non-sensitive files can be processed.

4. 🟠 SEM-004 — prompt_injection_subtle (HIGH)

  • Category: Prompt injection / scope override
  • Why this matched: This prompt could be manipulated by a user to inject misleading assumptions that could skew the analysis and lead to incorrect conclusions.
  • Rule intent: Subtle nudge to hide, mislead, or impersonate that regex couldn't catch
  • Matches in document: 1

Evidence (1 of 1 match):

Line 28:

- "What assumptions are we making about user behavior?"

Suggested fix: Add context or constraints around how assumptions about user behavior should be framed to prevent manipulation.

5. 🟠 SEM-007 — irreversible_action_no_confirmation (HIGH)

  • Category: Shell safety
  • Why this matched: The skill's output could lead to actions that significantly alter project direction without explicit user confirmation on the priority of questions.
  • Rule intent: Skill instructs the LLM to take an irreversible action without explicit user confirmation
  • Matches in document: 1

Evidence (1 of 1 match):

Line 63:

- **Questions** — 5–10 questions, prioritized by importance.

Suggested fix: Implement a confirmation step before finalizing the prioritized questions to ensure the user agrees with the proposed priorities.

6. 🟡 SEM-006 — credential_handling_unsafe (WARNING)

  • Category: Credential exposure
  • Why this matched: The priority levels could inadvertently expose sensitive project information if misused or logged without proper safeguards.
  • Rule intent: Credentials/tokens handled in ways that risk exposure (logging, echoing, including in prompts)
  • Matches in document: 1

Evidence (1 of 1 match):

Line 46:

- **Priority** — `critical` (blocks implementation), `high` (affects design), `medium` (good to know), `low` (nice to clarify)

Suggested fix: Ensure that any logging or output of priority levels does not include sensitive information and is handled securely.

Scope of this edition

The audit covers static rule matching, semantic-layer LLM analysis, and adversarial prompt fuzzing. Three classes of risk live beyond this edition's scope. We name them explicitly:

  • Runtime behavior. Verifying what a skill actually does at runtime requires sandboxed execution. That layer ships in a future edition; today's report reflects what the skill states it will do, plus the LLM's read of how it would behave.
  • Cross-skill composition. When this skill is chained with others through a planner, the emergent state flow between skills is its own analysis surface. Out of scope for single-skill reports.
  • External payloads. A skill that fetches and runs a remote script is flagged at the fetch step. The remote payload itself is audited as a follow-up once the sandbox layer is online.

Methodology

How the score was computed:

  1. Document text is scanned against a static rule set of 32 signature patterns. Each rule carries a permanent rule_id (e.g. PI-001), a category, a severity, and a remediation template.
  2. Each rule hit deducts from a 100-point base: critical -20, high -10, warning -5, info -1.
  3. The letter grade is gated by max severity AND total score: any critical → F; any high → at most D; any warning → at most C; otherwise A/B by score band.
  4. Per-category sub-scores apply the same deduction formula to that category's findings only — so you can see WHICH risk surface drove the loss.

Rule matches are augmented by an LLM-based semantic pass when an LLM endpoint is configured. The semantic pass uses rule IDs SEM-001SEM-008.

When an LLM endpoint is configured the skill is also probed with a 15-attack adversarial corpus (5 classes × 3 prompts), each judged by a separate LLM call. Failed classes surface as rule IDs AR-001AR-005.

Engine + rule set provenance:

  • Engine version: 0.2.0
  • Rule set version: 1.1.0
  • Commit: unknown
  • Domain config: general
  • Audited at: 2026-08-10T20:58:00.270577Z
  • Rules applied: 36 static rules (full registry below)
Full rule registry applied to this audit | Rule ID | Name | Category | Severity | |---|---|---|:---:| | `FA-001` | sensitive_file_access | file_access | warning | | `SS-001` | destructive_bash | shell_safety | high | | `SS-002` | force_flag_abuse | shell_safety | high | | `DE-001` | external_data_exfil | data_exfil | high | | `CE-001` | credential_in_content | credential_exposure | high | | `SS-003` | pipe_to_shell | shell_safety | critical | | `SS-004` | sudo_usage | shell_safety | warning | | `PI-001` | prompt_injection_bypass | prompt_injection | critical | | `PI-002` | hidden_instruction | prompt_injection | critical | | `PI-003` | excessive_permission_claim | prompt_injection | high | | `PI-004` | disable_safety_instruction | prompt_injection | high | | `PI-005` | impersonation_instruction | prompt_injection | high | | `MP-001` | encoded_payload | malicious_payload | warning | | `DE-002` | network_exfil_pattern | data_exfil | high | | `MP-002` | crypto_miner_pattern | malicious_payload | critical | | `MP-003` | reverse_shell_pattern | malicious_payload | critical | | `DE-003` | data_collection_broad | data_exfil | warning | | `QL-001` | shell_block_no_error_handling | quality | info | | `QL-002` | unpinned_install_command | quality | info | | `SEM-001` | semantic_evasion | prompt_injection | high | | `SEM-002` | ambiguous_instruction | prompt_injection | warning | | `SEM-003` | capability_overreach | prompt_injection | warning | | `SEM-004` | prompt_injection_subtle | prompt_injection | high | | `SEM-005` | unauthorized_data_flow | data_exfil | high | | `SEM-006` | credential_handling_unsafe | credential_exposure | high | | `SEM-007` | irreversible_action_no_confirmation | shell_safety | high | | `SEM-008` | external_payload_blind_trust | malicious_payload | high | | `AR-001` | instruction_override_failure | prompt_injection | high | | `AR-002` | role_jailbreak_failure | prompt_injection | high | | `AR-003` | hidden_payload_failure | malicious_payload | high | | `AR-004` | authority_spoof_failure | prompt_injection | high | | `AR-005` | reflective_injection_failure | prompt_injection | high | | `SUP-001` | typosquat_risk | supply_chain | high | | `SUP-002` | known_vulnerability | supply_chain | high | | `SUP-003` | unpinned_dependency | supply_chain | warning | | `SUP-004` | deprecated_or_yanked | supply_chain | warning |

Known limitations of this report

  • False positives are possible. A SKILL.md documenting a dangerous pattern (e.g. an audit skill explaining curl | sh) will match the rule even though the skill's intent is to detect, not execute. Read the matched lines before reacting.
  • False negatives are guaranteed in narrow ways. Patterns obfuscated by string concatenation, environment variable indirection, or non-English equivalents will slip past regex.
  • Baseline sample size. Same-skill trend analysis (§ Historical baseline) gets meaningful with n≥3 prior audits. With fewer priors the stddev band is widened to avoid false out-of-band signals.

About TAR Engine

TAR Engine is an OSS "wish machine" with built-in audit. Speak a goal; the engine plans, runs and audits skills inside its own container. BYOK. — github.com/qingxuantang/tar-engine

Audit your own skills

This report was produced by the open-source engine, running the same four layers on every skill in the directory. Point it at yours.

Paste one skill

Drop a SKILL.md into the Playground and read the verdict in about 30 seconds. Nothing to install.

Open the Playground

Gate it in CI

Three lines in your workflow. Every pull request gets audited, and the build fails below your threshold.

- uses: qingxuantang/tar-engine@v0.3.3
  with:
    path: ./skills
    min-score: 70

Private repositories

Org-wide CI enforcement, private repos, and a signed evidence pack per audited component — findings, dependency inventory, engine version and timestamp — for your security review. From €99/month.

Is story-questions safe?

Is story-questions safe to install?

story-questions scored 45/100 (grade D) in TAR Engine's automated safety audit. It carries notable safety risks — read the findings carefully before installing.

What safety risks does story-questions have?

TAR Engine audits story-questions for prompt injection, unsafe shell commands, file access, data exfiltration, credential exposure, malicious payloads, supply-chain risk and quality. The Findings section above lists the specific results.