alterlab-nmc-video-essay
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest untrusted data from external sources, which creates a potential vector for indirect prompt injection attacks.
- Ingestion points: In the 'Workflow' and 'Conceptual Development' sections of SKILL.md, the agent is directed to 'search the web for video essay examples', 'read existing project files', and 'read relevant criticism, theory, and journalism'.
- Capability inventory: The agent has the capability to perform web searches and write multiple structured markdown files to the local file system.
- Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between its core operating instructions and the external data it is tasked with processing.
- Sanitization: The skill does not outline any procedures for validating, filtering, or escaping content retrieved from the internet or local files before it is processed by the AI.
Audit Metadata