lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze the local codebase to understand the product's features and value proposition. This creates an attack surface where untrusted data (e.g., instructions embedded in README files, comments, or documentation within the repo) could influence the agent's behavior.
- Ingestion points: Local project directory/codebase files.
- Boundary markers: None specified in the instructions to delimit code from instructions.
- Capability inventory: File reading, web searching, and data formatting.
- Sanitization: No explicit sanitization or filtering of codebase content is mentioned before processing.
Audit Metadata