consult-action-fields

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run local scripts such as discover-projects.sh, engagement-status.sh, and deliverable-graph.py. These scripts are part of the plugin's internal directory and are used for project discovery and validation.
  • [PROMPT_INJECTION]: The skill processes project-specific data which creates an indirect prompt injection surface. Ingestion points: consult-project.json and field.json files. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in the workflow. Capability inventory: Uses the Bash tool to execute scripts with interpolated project paths. Sanitization: No explicit validation or sanitization of project-defined slugs or paths is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 01:51 PM
Security Audit — agent-trust-hub — consult-action-fields