matt-research
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: According to SKILL.md, the agent investigates external 'primary sources' including official documentation, source code, and first-party APIs.
- Boundary markers: The instructions lack specific delimiters or directions to ignore potentially malicious instructions found within the researched material.
- Capability inventory: The agent is empowered to write findings to the repository in Markdown format and modify existing project knowledge files (.tw entries).
- Sanitization: No sanitization or content validation steps are specified for the data retrieved from external sources before it is written back to the project files.
Audit Metadata