research
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of high-level instructions for research and documentation. It does not contain any executable scripts, remote code downloads, or hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves reading untrusted external data (primary sources like documentation and APIs). This is a standard attack surface for research-oriented skills.
- Ingestion points: External URLs and files accessed during background research tasks.
- Boundary markers: None specified in the instructions.
- Capability inventory: The agent is instructed to write a cited Markdown file to the repository.
- Sanitization: No specific sanitization or filtering steps are outlined for the ingested external content, relying on the agent's default processing behavior.
Audit Metadata