factory-supervision

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Python script scripts/validate_preflight.py that executes local git commands using the subprocess module to verify the state of a workspace.
  • The script implements security controls by validating all dynamic command components, such as Git object IDs, ensuring they are well-formed hexadecimal strings before use.
  • Subprocess calls are made with shell=False (the default) to prevent shell injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The validation script processes external JSON manifests which could potentially be manipulated by an attacker to influence the supervision logic.
  • Ingestion points: The validate_preflight.py script reads a JSON manifest file from a path provided via command-line arguments.
  • Boundary markers: The script uses structured JSON parsing rather than natural language delimiters.
  • Capability inventory: The script is limited to local file reads and execution of the git binary.
  • Sanitization: The script performs extensive validation, including type checking, strict length and character set verification for hashes, and path resolution checks to ensure relative paths do not escape the designated workspace directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 06:32 PM
Security Audit — agent-trust-hub — factory-supervision