alterlab-cdm-production-manager
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core workflow of processing external and untrusted data.
- Ingestion points: The agent is instructed to search the web for production templates and rate cards, and to read local project files such as screenplays, breakdown sheets, and director's notes (SKILL.md).
- Boundary markers: The skill lacks explicit boundary markers or specific instructions to the agent to treat ingested data as untrusted or to ignore embedded commands within those sources.
- Capability inventory: The agent possesses capabilities for web searching, reading the local file system, and writing structured markdown files to the project directory.
- Sanitization: There are no specified procedures for sanitizing, validating, or filtering content retrieved from the web or project files before it is processed by the agent.
Audit Metadata