forge-motion
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and modify user-supplied CSS code, which is a potential surface for indirect prompt injection.
- Ingestion points: The agent reads CSS animations and transitions from the user's project files as described in SKILL.md.
- Boundary markers: There are no instructions or delimiters provided to differentiate untrusted user data from agent commands.
- Capability inventory: The skill grants the agent file-writing capabilities to append media queries to CSS files.
- Sanitization: The skill lacks explicit validation, filtering, or sanitization for the code it processes.
Audit Metadata