ext-self-review-plan-marshall

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script uses subprocess.run to execute Git commands such as diff, merge-base, and rev-parse. These calls use a list-based argument format which prevents shell injection, and the operations are restricted to the Git binary within the project directory. Evidence found in scripts/_self_review_diff.py and scripts/self_review.py.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface (Category 8). It extracts raw strings, comments, and code snippets from unvetted source files and diffs to be processed by a downstream AI agent.
  • Ingestion points: Untrusted data enters the context via _diff_hunks (Git output) and _read_post_image (local file contents) in scripts/_self_review_diff.py.
  • Boundary markers: Absent. Extracted data is placed directly into structured TOON output fields (e.g., text, pattern, description) without delimiters or "ignore instructions" warnings.
  • Capability inventory: The skill performs file reads (_read_post_image) and subprocess calls to Git (subprocess.run).
  • Sanitization: Only length-based truncation (_truncate) is performed; there is no filtering or escaping of potential prompt-injection keywords or instructions in the extracted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 07:13 AM
Security Audit — agent-trust-hub — ext-self-review-plan-marshall