project-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: This skill is vulnerable to indirect prompt injection because it processes untrusted data from software projects. Malicious instructions hidden in comments, documentation, or source code could influence the agent's actions.
- Ingestion points: Data enters the agent's context through the output of
scripts/analyze_project.pyand through the agent's recommended workflow of reading project files (e.g., README.md, entry points, configuration). - Boundary markers: The instructions do not define boundary markers or clear separators to distinguish between user instructions and data from the project files.
- Capability inventory: The skill enables the execution of a custom Python script and shell commands like
grep, while also requiring the agent to read various files from the user-provided directory. - Sanitization: No sanitization or filtering is performed on the content of the analyzed project files before they are processed by the agent.
Audit Metadata