skills/jeremylongshore/claude-code-plugins-plus-skills/evaluating-machine-learning-models/Gen Agent Trust Hub
evaluating-machine-learning-models
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it is designed to ingest and process untrusted external data which could influence agent behavior.
- Ingestion points: External datasets (e.g., CSV files) are loaded and processed by the skill, specifically within
assets/visualization_script.py(viapandas.read_csv) and the referenceddata_loader.pyscript. - Boundary markers: The instructions do not define clear boundaries or provide guidance for the agent to ignore potentially malicious instructions embedded within the data files.
- Capability inventory: The skill is configured with broad access to system tools, including
Bash(cmd:*),Write,Edit,Grep, andGlob(as defined in theSKILL.mdfrontmatter). - Sanitization: No sanitization or validation mechanisms are implemented to filter or escape content from the ingested datasets before they are processed in the agent's context.
Audit Metadata