command-dispatch
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural language input to perform state-changing API actions. \n
- Ingestion points: User natural language requests and slash commands (SKILL.md). \n
- Boundary markers: Absent. \n
- Capability inventory:
moviepilot_apitool withslash.runandplugin.capabilities(SKILL.md). \n - Sanitization: Present; instructions mandate matching against a live catalog, prohibit inventing arguments, and require explicit user confirmation.
Audit Metadata