preflight
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the contents of local source files identified via
git diff. If these files contain adversarial instructions (e.g., hidden in comments), they could potentially influence the agent's behavior during the review process. - Ingestion points: Local source code files identified by the
git diff main --name-onlycommand (SKILL.md instructions). - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions to isolate the data being analyzed from the agent's internal logic.
- Capability inventory: The skill has the ability to execute shell commands including
git,make, andpnpm(SKILL.md code blocks). - Sanitization: Absent. The skill reads and evaluates raw file content directly.
- [COMMAND_EXECUTION]: The skill instructs the agent to run shell commands to perform type checking and dependency audits.
- Evidence: Usage of
git diff main --name-only,make types,pnpm tsc --noEmit, andpnpm auditwithin the instruction and check sections.
Audit Metadata