code-review-pro
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including Pull Request content, Git history, and Jira/GitHub tickets, creating an attack surface for indirect prompt injection.
- Ingestion points: Pull Request code, Git history, and associated tickets (identified in SKILL.md).
- Boundary markers: The instructions do not define delimiters or explicit 'ignore embedded instructions' warnings for the data being reviewed.
- Capability inventory: The agent is instructed to activate additional skills (auditor-pro, strict-auditor), use the codebase_investigator tool, and execute local scripts (scripts/pr-audit.ts, scripts/trace-dependency-impact.py).
- Sanitization: No sanitization, escaping, or validation of the ingested external content is specified.
- [COMMAND_EXECUTION]: The skill documentation references the execution of local scripts and build tools as part of its auditing workflow.
- Evidence: Mentions execution of 'scripts/pr-audit.ts' for generating reports, 'scripts/trace-dependency-impact.py' for dependency visualization, and 'bun run build --profile' for performance auditing (identified in SKILL.md and references/performance-audit.md).
Audit Metadata