test-gap-audit
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external data from the repository being audited. 1. Ingestion points: The skill reads pull request descriptions, branch names, feature descriptions, and source code content as specified in the 'Inputs' section of SKILL.md. 2. Boundary markers: The instructions lack explicit delimiters or instructions to treat external data as untrusted or to ignore embedded instructions within that data. 3. Capability inventory: The skill has the ability to execute shell commands (git, grep, lint) and modify files in the repository during the 'Post-Audit Test Implementation' phase. 4. Sanitization: No sanitization or validation of the audited content is performed before processing or interpreting it.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute various shell commands for environment discovery and verification. Evidence: The 'Discovery Workflow' and 'Verify safely' sections in SKILL.md include commands such as git status, grep, search, typecheck, and lint.
Audit Metadata