application-security-review
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides high-quality, defensive security auditing instructions intended to help an agent evaluate the security posture of third-party repositories. It covers critical areas like trust boundaries, auth flow, and data handling.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from external repositories (source code, READMEs, manifests, and git history). This creates a potential surface for indirect prompt injection where malicious content in an audited repository could attempt to subvert the agent's logic. The risk is considered part of the skill's primary function and is mitigated by the skill's instructions to focus on objective evidence.
- Ingestion points: Audited repository files, metadata, and git history (Workflow section in SKILL.md).
- Boundary markers: No explicit instruction to wrap repository content in delimiters during analysis to prevent the agent from obeying embedded instructions.
- Capability inventory: File system read and search capabilities, and potential execution of auditing tools (e.g., npm audit).
- Sanitization: The skill does not define specific sanitization or filtering logic for the code it audits before the agent processes it.
Audit Metadata