feature-importance-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze machine learning training patterns and operations, which involves ingesting potentially untrusted data that could contain malicious instructions.
- Ingestion points: Processes user-provided requests and machine learning data patterns in SKILL.md instructions.
- Boundary markers: The instructions do not define explicit delimiters or use "ignore embedded instructions" warnings for the data being analyzed.
- Capability inventory: The skill is granted access to high-privilege tools including
Bash(python:*),Bash(pip:*),Read,Write, andEdit. - Sanitization: There are no specified sanitization, validation, or filtering mechanisms for the external machine learning content being processed.
Audit Metadata