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 (via pandas.read_csv) and the referenced data_loader.py script.
  • 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, and Glob (as defined in the SKILL.md frontmatter).
  • 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
Risk Level
SAFE
Analyzed
Apr 4, 2026, 09:56 AM