researcher
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to retrieve and process untrusted external data from the web and GitHub repositories.
- Ingestion points: Content retrieved from external libraries, APIs, and open-source code repositories.
- Boundary markers: While the skill emphasizes citing sources and marking unverified claims, it lacks specific technical delimiters to isolate retrieved content from the agent's internal instructions.
- Capability inventory: The skill references environment capabilities such as web search, documentation retrieval, and shell access (SKILL.md).
- Sanitization: There are no instructions for sanitizing or filtering instructions that might be embedded in the retrieved external data.
Audit Metadata