Skills
Navigate
skills/pluginagentmarketplace/custom-plugin-ai-data-scientist/python-programming/Gen Agent Trust Hub

python-programming

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external files (CSV, JSON, Parquet) and SQL databases, which is a standard surface for indirect prompt injection if the input files contain instructions intended to influence the agent's behavior.
  • Ingestion points: SKILL.md, references/PANDAS_CHEATSHEET.md, and scripts/data_processor.py all use ingestion methods like pd.read_csv, pd.read_json, and pd.read_parquet.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the provided snippets.
  • Capability inventory: The skill has the capability to write to the local filesystem using to_csv and to_parquet in scripts/data_processor.py and perform SQL queries via pd.read_sql_query in SKILL.md.
  • Sanitization: scripts/data_processor.py includes a clean_column_names method that sanitizes column headers using regex, though it does not sanitize the data content itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 01:40 PM