early-stopping-callback
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied requests and data related to machine learning training, which could potentially contain malicious instructions.
- Ingestion points: User requests containing keywords like 'early stopping callback' or 'ml training' as seen in SKILL.md.
- Boundary markers: The skill instructions do not specify any delimiters or safety markers to differentiate between user data and system instructions.
- Capability inventory: The skill is configured with broad tool access including Read, Write, Edit, and Bash (python and pip), allowing it to modify files and execute code.
- Sanitization: There are no explicit instructions to sanitize or validate the content of the ML configurations or code snippets generated from user input.
Audit Metadata