Skills
skills/doanchienthangdev/omgkit/data-engineering/Gen Agent Trust Hub

data-engineering

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The version_data function in SKILL.md uses subprocess.run to call dvc and git. This allows the agent to interact with the host filesystem and version control systems.\n- [PROMPT_INJECTION]: The skill ingests data from external sources using requests.get and pd.read_sql in SKILL.md, creating an indirect prompt injection surface. 1. Ingestion points: API responses and SQL database results. 2. Boundary markers: Absent. 3. Capability inventory: Subprocess execution (subprocess.run), network requests (requests.get), and database interaction (pd.read_sql). 4. Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:06 AM