document-existing-project
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted third-party codebases, which creates a vulnerability surface for indirect prompt injection where malicious instructions embedded in source code could attempt to influence the agent. 1. Ingestion points: The skill analyzes entry points, configuration files, dependencies, and existing documentation across the project directory (SKILL.md). 2. Boundary markers: The instructions do not mandate specific delimiters or boundary warnings when the agent processes file content. 3. Capability inventory: The skill can read any file in the project and write sharded documentation to the local filesystem. 4. Sanitization: There is no mention of sanitization or filtering of codebase content before it is processed by the agent.
- [DATA_EXFILTRATION]: The skill is instructed to locate and analyze configuration files such as .env.example and environment setup requirements to document the project's state. While this is necessary for its function, it involves accessing potentially sensitive metadata about the project environment.
Audit Metadata