review

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from git diffs, commit logs, and external issue trackers, which could contain instructions designed to manipulate the sub-agents' analysis (Indirect Prompt Injection). \n
  • Ingestion points: Content is ingested from git diff outputs, git log commit messages, and external specification files or issue trackers referenced in Step 2. \n
  • Boundary markers: The prompts for the 'Standards' and 'Spec' sub-agents do not include specific delimiters or 'ignore' instructions for the content being reviewed, increasing the risk that the AI may follow instructions embedded within the data. \n
  • Capability inventory: The skill can read repository files, execute git commands, and spawn general-purpose sub-agents to process analyzed data. \n
  • Sanitization: There is no evidence of sanitization or validation applied to the content of diffs or fetched issues before they are passed to the sub-agent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 10:39 PM
Security Audit — agent-trust-hub — review