alterlab-cdm-preproduction
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, which creates a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read external screenplay files, director's notes, and location references as part of the primary workflow (SKILL.md, Workflow step 1).
- Boundary markers: The skill definition does not provide specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the text of the scripts it reads.
- Capability inventory: The agent has permissions to write multiple markdown deliverables to the local file system and perform web searches for research.
- Sanitization: No explicit sanitization or validation of the ingested script content is required before the data is integrated into the agent's context for planning.
Audit Metadata