polymorph
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and maps external data and code representations, creating a potential surface for instructions embedded in source artifacts to influence the agent's behavior.\n
- Ingestion points: User-supplied source artifacts like CSV, JSON, code, or specifications (SKILL.md).\n
- Boundary markers: Step 1 of the procedure requires identifying success conditions and "no-touch boundaries" before taking action (SKILL.md).\n
- Capability inventory: The skill uses standard agent capabilities for mapping and conversion without requiring network access or high-privilege shell commands (SKILL.md).\n
- Sanitization: The instructions do not specify mechanisms for sanitizing or escaping content within the source artifacts (SKILL.md).
Audit Metadata