motion-plan
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional, providing logic for an AI agent to classify and describe video shots. It contains no scripts, binary files, or network-enabled commands.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external scripts and transcripts, creating an ingestion point for untrusted data. However, the skill lacks the capabilities required for a successful attack.\n
- Ingestion points: User-provided scripts and transcripts in SKILL.md.\n
- Boundary markers: None provided.\n
- Capability inventory: None; the skill does not use shell, python, or network tools.\n
- Sanitization: None.
Audit Metadata