Skills
skills/jst-well-dan/skill-box/csv-data-summarizer/Gen Agent Trust Hub

csv-data-summarizer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The SKILL.md file uses directive language such as '⚠️ CRITICAL BEHAVIOR REQUIREMENT ⚠️' and 'FORBIDDEN BEHAVIORS' to explicitly bypass the agent's conversational guardrails and clarification protocols.
  • Indirect Prompt Injection (LOW): Attack surface identified. 1. Ingestion points: The summarize_csv function in analyze.py reads user-provided CSV files. 2. Boundary markers: Absent; there are no instructions to the agent to distinguish data content from instructions. 3. Capability inventory: Subprocess file writing for image generation (plt.savefig). 4. Sanitization: Absent; raw data is ingested and summarized directly.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM