Skills
Navigate
skills/ovachiever/droid-tings/csv-data-summarizer/Gen Agent Trust Hub

csv-data-summarizer

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The instructions in SKILL.md use aggressive and imperative language ("⚙️ CRITICAL BEHAVIOR REQUIREMENT ⚙️", "FORBIDDEN BEHAVIORS", "JUST DO IT") to override standard assistant behavior and safety-oriented conversational patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided CSV data and automatically executes analysis, creating a surface for potential data-driven instruction injection.
  • Ingestion points: The summarize_csv function in analyze.py reads user-provided files using pandas.read_csv.
  • Capability inventory: The skill performs file system write operations (plt.savefig) in analyze.py to create multiple PNG visualizations.
  • Sanitization: No content validation or sanitization is performed on the CSV data before it is processed or visualized.
  • Boundary markers: The skill lacks explicit delimiters or instructions to prevent the agent from following directives embedded within the CSV data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:16 PM