wiki-qa
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes content from external source files, which creates a surface for indirect prompt injection where malicious instructions embedded in those files could influence the agent's behavior.
- Ingestion points: The agent searches and reads files within the repository codebase as specified in the Procedure section of
SKILL.md. - Boundary markers: Present. The Rules section in
SKILL.mdinstructs the agent to ONLY use information from actual source files and NEVER to invent or guess information, serving as a behavioral constraint. - Capability inventory: The skill utilizes file system search and read capabilities to gather evidence from the repository (
SKILL.md). - Sanitization: Absent. The skill does not implement sanitization or validation of the file contents before processing them to generate a response.
Audit Metadata