security-best-practice
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by scanning user project files, including configuration files and existing authentication route handlers, as specified in the 'Detect Project Context' step. An attacker could embed malicious instructions within these files to influence the agent's audit findings or the fixes it applies.
- Ingestion points: Framework configuration files (e.g., package.json, next.config.*) and route handler source code in the user's project.
- Boundary markers: The skill does not implement explicit boundary markers or instructions for the agent to ignore embedded commands when reading user files.
- Capability inventory: The agent has permissions to read files and apply fixes directly to the project code.
- Sanitization: There is no evidence of content sanitization or validation of the ingested code before it is processed by the agent.
Audit Metadata