to-scenes
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process content from user-controlled files (
BEATS.mdandNARRATION.md) to generate new files or modify existing ones. It does not include instructions to isolate this data or ignore embedded commands, creating a potential surface for indirect prompt injection where malicious content in the input files could influence the agent's actions. - Ingestion points: The process begins by reading
BEATS.mdandNARRATION.md(SKILL.md, Step 1). - Boundary markers: The instructions do not define clear boundaries or use delimiters to distinguish between the skill's instructions and the data being processed.
- Capability inventory: The agent has the capability to write to the file system, specifically creating
SCENES.mdand revisingNARRATION.md(SKILL.md, Steps 5 and 6). - Sanitization: There is no evidence of input validation or sanitization to ensure the user-provided data does not contain harmful instructions meant for the AI agent.
Audit Metadata