research-and-teach
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from the web to perform research, which introduces a surface for indirect prompt injection attacks.
- Ingestion points: The
SKILL.mdfile (Step 2: Research) instructs the agent to "Search strategically" and "Fetch sources" using external tools. - Boundary markers: The instructions lack explicit delimiters or warnings to treat fetched content as untrusted data.
- Capability inventory: The skill uses web fetching capabilities and outputs processed information to the user.
- Sanitization: There are no instructions for sanitizing or filtering instructions that might be embedded in the external research sources.
Audit Metadata