qa-evidence-bundle
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes Bash, Grep, and Read tools to scan and aggregate YAML output files from other QA child skills within the project directory.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface as it processes external YAML data produced by other skills. However, it mitigates risk by applying deterministic logic for decision-making rather than relying on LLM interpretation of the aggregated data.
Audit Metadata