mcp-autopentest-orchestrator

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script ../../autonomy/probe_runner.py to perform core security assessment tasks. This is a functional requirement of the orchestrator and is restricted to the local filesystem.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and reasons over findings from external probe results (JSON findings). This is a low-risk surface inherent to the tool's purpose of analyzing security data. Ingestion points: JSON output from the probe_runner.py script and structured reports from sub-agents in SKILL.md. Boundary markers: The instructions specify processing 'structured results' and JSON data. Capability inventory: The skill can execute local Python scripts and spawn read-only sub-agents. Sanitization: Not explicitly defined in the skill instructions, though human-in-the-loop checkpoints are required for high-risk actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 04:29 PM
Security Audit — agent-trust-hub — mcp-autopentest-orchestrator