alterlab-cdm-festival-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project files like screenplays and director's notes, as well as information gathered from web searches, which constitutes an ingestion surface for untrusted data. 1. Ingestion points: Project files (screenplays, notes) and web content. 2. Boundary markers: Absent. 3. Capability inventory: File reading, file writing, and web searching. 4. Sanitization: None identified.
- [COMMAND_EXECUTION]: The skill uses file system tools to write various markdown deliverables (e.g., press kits and calendars) to the user's project directory as its primary function.
Audit Metadata