qa-static-baseline
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files and command-line outputs during its quality gate process.
- Ingestion points: The skill reads project source code and captures stdout/exit codes from tools such as ESLint, tsc, and npm audit (SKILL.md §3, §5).
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded in the code or linting reports it processes.
- Capability inventory: The skill uses Bash and Read tools to execute scripts and analyze files, which could theoretically be triggered by malicious patterns in the ingested data.
- Sanitization: The skill does not specify sanitization or filtering of tool outputs before they are processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references and integrates well-known security tools from external sources.
- References the git-secrets tool from the official AWS Labs GitHub repository.
- References the TruffleHog secret scanning tool from the Truffle Security GitHub repository.
- These tools and their associated repositories are recognized as trusted or well-known security services.
Audit Metadata