ducky
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied code and descriptions to facilitate debugging, creating a surface for indirect prompt injection. The skill's strict constraints (responding only with questions) act as a significant mitigation against instructions embedded in user data.
- Ingestion points: User-provided code and chat input processed by the agent in SKILL.md.
- Boundary markers: The skill does not provide specific instructions for the agent to use delimiters or ignore instructions within the user-provided data.
- Capability inventory: The skill notes that existing tool use and code execution capabilities are allowed for the purpose of gathering information.
- Sanitization: The instructions do not define any validation or sanitization procedures for the user-supplied content.
Audit Metadata