research
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a process for investigating questions against high-trust primary sources (official docs, source code, specs) and capturing findings in Markdown. The behavior matches the stated purpose of a research tool.
- [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting data from external primary sources which provides a surface for indirect prompt injection.
- Ingestion points: External websites, documentation, and APIs referenced during research (SKILL.md).
- Boundary markers: None explicitly defined in the prompt template.
- Capability inventory: The agent is authorized to write Markdown files to the repository and dispatch background tasks via internal tools.
- Sanitization: The skill mitigates risks by instructing the agent to 'follow every claim back to the source that owns it' and 'cite each claim's source', encouraging verification of external data.
Audit Metadata