df-basic-stats

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands for dependency installation and running the analysis script. These are standard operations for the skill's purpose. \n- [EXTERNAL_DOWNLOADS]: The skill downloads well-known libraries (pandas, numpy, matplotlib, ydata-profiling) from the official PyPI registry, which is a trusted source. \n- [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill processes external data and generates a report for the agent to interpret. \n
  • Ingestion points: The load_dataframe function in scripts/compute_stats.py reads user-provided files (CSV, Excel, Parquet, JSON, etc.). \n
  • Boundary markers: The generated Markdown report does not use specific delimiters or instructions to isolate data content from the agent's logic. \n
  • Capability inventory: The skill has the ability to read local files, write reports, and generate distribution charts on the file system. \n
  • Sanitization: Data content from input files is formatted into the report without explicit sanitization against potential instructions embedded in the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 01:58 PM