draft-validation

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill uses exec() within the EditValidation.accept() method to process and run Python code generated or modified by an LLM.
  • Evidence: SKILL.md states: "accept() runs the revised code with exec(). Read it with to_code() or review() first..."
  • Mitigations: The skill implements validate_syntax() which checks if the code parses and ensures only permitted validation methods are used before execution. It also provides edit.review() and edit.diff() for human-in-the-loop verification.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data summaries and natural language instructions via LLMs to generate code, creating an attack surface for indirect prompt injection if the processed data contains malicious instructions.
  • Ingestion points: df (dataframes) processed via DataScan and user-provided instruction strings in EditValidation.
  • Boundary markers: The skill notes that models only see a JSON summary of the table, not raw rows, reducing the injection surface.
  • Capability inventory: Can perform file reads (YAML/Python paths) and execute code via exec().
  • Sanitization: Employs validate_syntax() to restrict the generated code to known pointblank validation methods.
  • [COMMAND_EXECUTION]: The skill documents terminal-based interactive sessions and environment variable management for API keys.
  • Evidence: Documentation for pb.assistant(display="terminal") and export commands for API keys in references/providers-reference.md.
  • [CREDENTIALS_UNSAFE]: The documentation shows examples of hardcoding API keys, though it explicitly recommends using environment variables as a safer alternative.
  • Evidence: SKILL.md contains a placeholder example api_key="sk-...". The instructions correctly guide users to store secrets in .env files or environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 07:27 AM