gitcode-pr-security-review
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code content from GitCode Pull Requests, which creates an attack surface for indirect prompt injection where malicious code could attempt to influence the audit results.
- Ingestion points: Untrusted code patches are retrieved from GitCode PRs in
SKILL.md(Step 4.1) and processed viascripts/gitcode_api.py. - Boundary markers: Absent. There are no explicit delimiters or instructions to ignore embedded directives when passing PR code to the
sdk-security-auditskill or the internal fallback logic. - Capability inventory: The skill can create comments on external Pull Requests using the GitCode API (
POST /pulls/{number}/comments). - Sanitization: No sanitization is performed on the PR code before it is interpreted by the LLM for analysis.
- Mitigation: The skill implements a human-in-the-loop requirement in
SKILL.md(Step 4.5), which requires the user to review and confirm all findings before any comments are posted to the repository.
Audit Metadata