qa-risk-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools such as git (diff, log, stat) and grep to perform impact analysis and calculate change frequency. These commands are used for their intended purpose of analyzing local repository metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data which constitutes a potential injection surface. 1. Ingestion points: The skill parses git diff output, coverage reports (Istanbul, JaCoCo, coverage.py), and project configuration files as described in references/impact-analysis.md. 2. Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are specified in the provided files. 3. Capability inventory: The skill provides instructions for local command execution (git, grep, radon, eslint) to gather metrics but does not perform file writes or network operations. 4. Sanitization: No explicit sanitization or validation logic for the ingested data is documented. This finding is documented for transparency regarding the skill's input surface.
Audit Metadata