to-scenes
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that processes untrusted data from external files. Ingestion points: BEATS.md and NARRATION.md are read as primary inputs in the SKILL.md process. Boundary markers: No explicit delimiters or instructions to disregard embedded commands are provided. Capability inventory: No hazardous tools, shell execution, or network operations are included in the skill; logic is strictly limited to text transformation. Sanitization: No input validation or filtering is specified for the processed content.
Audit Metadata