research
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources (official documentation, APIs, and source code) and write the output to the repository, creating an attack surface.\n- Ingestion points: External data is retrieved from primary sources specified in the user's research request as described in
SKILL.md.\n- Boundary markers: The instructions do not include delimiters or specific guidance to ignore potential instructions embedded within the investigated sources.\n- Capability inventory: The skill involves writing research findings to Markdown files in the local repository and accessing network resources to perform investigations.\n- Sanitization: No content sanitization, escaping, or validation steps are defined for the data retrieved from external sources before it is stored.
Audit Metadata