codebase-audit
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reviews entire codebases without sanitization or boundary markers. Malicious content in source files could influence the audit report or subsequent PRs.
- Ingestion points: All source files in the target directory read by the subagent.
- Boundary markers: Absent; the skill does not use delimiters to wrap untrusted content.
- Capability inventory: GitHub API access for issues and PRs, git push capabilities, and local execution of npm scripts.
- Sanitization: Absent; findings are directly included in GitHub communication templates.
- [COMMAND_EXECUTION]: The skill executes repository-specific build and test scripts (npm run build, npm run test) which can run arbitrary code defined in the target repository's configuration.
Audit Metadata