questioning
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user-provided questions which can act as a vector for instructions that influence the agent or its sub-agents.
- Ingestion points: User questions provided via the
/questioncommand or referenced skills (SKILL.md, Step 1). - Boundary markers: No explicit boundary markers or delimiters are defined to separate user-provided content from the skill's operational instructions.
- Capability inventory: The skill has the ability to read codebase files, invoke sub-agents for web research and codebase analysis, and write markdown files to a
thoughts/directory (SKILL.md, Steps 2 & 4). - Sanitization: There is no explicit sanitization or validation logic for the user-provided question or the topic slug used in file path construction.
Audit Metadata