ml-training-recipe
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external, untrusted sources including research papers, documentation, and code.\n
- Ingestion points: External research papers, datasets, documentation, and code repositories mentioned in the skill description (SKILL.md).\n
- Boundary markers: No specific delimiters or boundary instructions are defined to separate external data from agent instructions.\n
- Capability inventory: The skill utilizes 'researcher' and 'verifier' agents to gather and rank information, with results written to a local 'outputs/' directory.\n
- Sanitization: There are no explicit sanitization, validation, or filtering mechanisms described to handle malicious prompts embedded in the ingested data.
Audit Metadata