devsecops
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external repositories, CI/CD pipeline files, and deployment manifests. These external inputs are attacker-controllable and could contain hidden instructions intended to override agent behavior.
- Ingestion points: SKILL.md instructions to "Inspect the repo, pipeline files, deployment manifests" and "Map the path from commit to production".
- Boundary markers: Absent. The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the files being analyzed.
- Capability inventory: The skill does not provide custom scripts, relying instead on the platform's default tools to perform inspections and suggest remediations.
- Sanitization: Absent. There are no instructions for the agent to sanitize or validate the content of the files it reads.
- [NO_CODE]: The skill package contains no executable scripts (Python, JavaScript, shell scripts) or compiled binaries. The logic is delivered entirely through natural language instructions in markdown, which minimizes the direct execution risk.
Audit Metadata