maf-adapter

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to run a local Python script (test_harness.py) for validating plugin manifests and simulating skill execution. These commands are limited to local script execution and are part of the core functionality.
  • [PROMPT_INJECTION]: The test harness processes external input files and skill directories for validation. This establishes a surface for indirect prompt injection where malicious instructions could be embedded in the data being tested.
  • Ingestion points: SKILL.md (command line arguments --input and --skill).
  • Boundary markers: Not explicitly defined in the documentation.
  • Capability inventory: SKILL.md (executes Python scripts for simulation).
  • Sanitization: No sanitization logic is described in the provided markdown content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:07 PM
Security Audit — agent-trust-hub — maf-adapter