wiki-researcher
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a purely instructional prompt designed to guide an AI agent through a multi-step codebase analysis workflow. It does not include any scripts, executables, or network-bound commands.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing external codebase files which may contain untrusted data.
- Ingestion points: Files within the target codebase being researched (SKILL.md).
- Boundary markers: None explicitly defined in the instructions to separate untrusted code comments from agent instructions.
- Capability inventory: The skill itself does not define or request specific dangerous tools (like shell execution or network requests) in its frontmatter, relying on the agent's base capabilities.
- Sanitization: There are no explicit sanitization or escaping instructions for the data read from the codebase.
Audit Metadata