lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts, binaries, or configuration files.
- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection by design, as it analyzes local repository content.
- Ingestion points: User-provided codebase and repository files.
- Boundary markers: None; the instructions do not specify delimiters for the analyzed code.
- Capability inventory: None; the skill contains no executable code or scripts that could be leveraged.
- Sanitization: None; there is no instruction to filter or sanitize the content of the analyzed files.
Audit Metadata