research
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, credential harvesting, or unauthorized remote code execution detected. The skill uses standard web search and fetch tools for their intended purpose of researching documentation.- [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface due to the ingestion of web data, but this is a core requirement of its research functionality.
- Ingestion points: External data is ingested via WebSearch and WebFetch tools as defined in SKILL.md.
- Boundary markers: There are no explicit delimiters used to isolate fetched web content from the agent's internal reasoning.
- Capability inventory: The skill possesses the 'Read' and 'Write' capabilities to save research notes to the filesystem.
- Sanitization: No explicit sanitization or filtering of fetched documentation content is implemented.
Audit Metadata