Audit Report: triage-issue — 🟠 D (54/100)

Audited by TAR Engine · 2026-08-01 · 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/NousResearch/OpenShell/blob/main/.agents/skills/triage-issue/SKILL.md

Verdict: High risk — 3 high-severity issues need author attention before deploying to a shared environment.

What this skill does

Auditor's read (LLM-generated): The triage-issue skill assesses and classifies community-filed issues by processing either a specific issue or all open issues labeled with state:triage-needed. It validates compliance with an agent-first gate, performs diagnostics using relevant skills, and classifies issues for routing into the spike-build pipeline. The skill produces structured comments detailing the classification, summary of findings, and recommendations for next steps, while ensuring that human intervention is required for final approval on issue readiness.

Author description: Assess, classify, and route community-filed issues. Takes a specific issue number or processes all open issues with the state:triage-needed label in batch. Validates agent-first gate compliance, attempts diagnosis using relevant skills, and classifies issues for routing into the spike-build pipeline. Trigger keywords - triage issue, triage, assess issue, review incoming issue, triage issues.

Observed: triage-issue is 11 top-level sections (Prerequisites, Critical: state:agent-ready Label Is Human-Only, Agent Comment Marker, Invocation Modes, Step 1: Fetch the Issue, …); ~180 lines of instructions, concise body.

Frontmatter facts:

• Body size: 180 lines / 7223 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.

Historical baseline (same-skill comparison)

• Prior audits on record: 1 (first 2026-06-25T20:36:20.718449Z, most recent prior 2026-06-25T20:36:20.718449Z)
• Score statistics: mean 34.0 ± 0.0 (range 34–34) (normal band: 31.0 – 37.0)
• This audit vs last: +20 (📈 improved)
• Out-of-band notice: this score is outside the skill's historical normal band — worth a closer read.
• Top recurring findings across history:
• SEM-006 — hit in 1 of 1 prior audits (100.0%)
• SEM-008 — hit in 1 of 1 prior audits (100.0%)
• SEM-002 — hit in 1 of 1 prior audits (100.0%)
• SEM-004 — hit in 1 of 1 prior audits (100.0%)
• SEM-003 — hit in 1 of 1 prior audits (100.0%)

Baseline assumes the skill's name + description haven't changed. A rename or rewrite starts a fresh baseline.

Findings

7 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: The skill fetches issue details without validating the content, which could lead to processing malicious or misleading information if the issue was tampered with.
• 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 61:

gh issue view <id> --json title,body,state,labels,author,comments

Suggested fix: Add validation checks to ensure that the fetched issue data meets expected formats and contains no harmful content before proceeding with further actions.

2. 🟠 SEM-002 — ambiguous_instruction (HIGH)

• Category: Prompt injection / scope override
• Why this matched: The instruction to load various skills is vague and could lead a user to load a skill that performs unintended actions, especially if they misunderstand the context or capabilities of those skills.
• Rule intent: Ambiguous instruction that could be exploited as a prompt injection primitive
• Matches in document: 1

Evidence (1 of 1 match):

Line 94:

Your agent can load skills like `debug-openshell-cluster` (for cluster issues), `debug-inference` (for inference setup issues), `openshell-cli` (for usage questions), or `generate-sandbox-policy` (for policy help).

Suggested fix: Clarify the instructions by specifying the conditions under which each skill should be loaded and what actions they are intended to perform, ensuring users understand the implications of using each skill.

3. 🟠 SEM-007 — irreversible_action_no_confirmation (HIGH)

• Category: Shell safety
• Why this matched: The command to add a label to an issue is irreversible and does not require explicit user confirmation, which could lead to unintended modifications of issue states.
• 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 86:

gh issue edit <id> --add-label "state:triage-needed"

Suggested fix: Implement a confirmation step before executing the command to add a label, ensuring that the user explicitly agrees to the action.

4. 🟡 SEM-006 — credential_handling_unsafe (WARNING)

• Category: Credential exposure
• Why this matched: The skill assumes that the user has authenticated the GitHub CLI without specifying how to handle credentials securely, which could lead to exposure if not managed properly.
• 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 12:

The `gh` CLI must be authenticated (`gh auth status`)

Suggested fix: Provide clear guidance on how to authenticate securely and emphasize the importance of not exposing credentials in logs or outputs.

5. 🟡 SEM-004 — prompt_injection_subtle (WARNING)

• Category: Prompt injection / scope override
• Why this matched: The phrasing could be exploited by a malicious user to manipulate the agent into executing unintended commands or actions under the guise of investigation.
• Rule intent: Subtle nudge to hide, mislead, or impersonate that regex couldn't catch
• Matches in document: 1

Evidence (1 of 1 match):

Line 94:

OpenShell is an agent-first project - before we triage this, please point your coding agent at the repo and have it investigate.

Suggested fix: Rephrase the instruction to be more explicit about what actions the agent should take and include safeguards against executing arbitrary commands based on user input.

6. 🟡 SEM-003 — capability_overreach (WARNING)

• Category: Prompt injection / scope override
• Why this matched: The skill invokes a sub-agent that may have broader capabilities than necessary for triaging issues, potentially leading to misuse or unintended consequences.
• Rule intent: Capability claim over-broad relative to the skill's stated purpose
• Matches in document: 1

Evidence (1 of 1 match):

Line 106:

Use the `principal-engineer-reviewer` sub-agent via the Task tool:

Suggested fix: Limit the capabilities of the sub-agent to only those necessary for the triage process and clearly define its scope of actions to prevent overreach.

7. 🔵 QL-001 — shell_block_no_error_handling (INFO)

• Category: quality
• Why this matched: Shell block missing set -e / || exit — silent failures will go unreported
• Rule intent: Shell code blocks without set -e or explicit error handling
• Matches in document: 3

Evidence (3 of 3 matches):

Line 50:

     49: 
>>   50: ```bash
>>   51: gh issue list --label "state:triage-needed" --state open --json number,title --jq '.[].number'
>>   52: ```
     53: 

Line 60:

     59: 
>>   60: ```bash
>>   61: gh issue view <id> --json title,body,state,labels,author,comments
>>   62: ```
     63: 

Line 85:

     84: 1. Add the `state:triage-needed` label if not already present:
>>   85:    ```bash
>>   86:    gh issue edit <id> --add-label "state:triage-needed"
>>   87:    ```
     88: 2. Post a comment with the triage marker:

Suggested fix: Add set -euo pipefail at the top of bash blocks, or chain critical commands with || exit 1. Skills that fail silently mid-script are nearly impossible to debug downstream.

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-001 … SEM-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-001 … AR-005.

Engine + rule set provenance:

• Engine version: 0.2.0
• Rule set version: 1.1.0
• Commit: unknown
• Domain config: general
• Audited at: 2026-08-01T20:21:37.195420Z
• Rules applied: 36 static rules (full registry below)

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