quick-question
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of purely instructional markdown aimed at providing brief technical clarifications. It contains no executable scripts, shell commands, or network requests. Evidence: SKILL.md, evals/evals.json.- [INDIRECT_PROMPT_INJECTION]: The skill handles user queries as its primary input. The potential for malicious input to cause harm is neutralized by the skill's explicit rules forbidding file modifications, artifact creation, or tool usage (e.g., ask_question). Ingestion points: User queries. Boundary markers: Absent. Capability inventory: None (explicitly prohibited). Sanitization: N/A. Evidence: SKILL.md.
Audit Metadata