skills/syabro/mdtask/mdtask-add/Gen Agent Trust Hub

mdtask-add

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the mdtask command-line utility to manage task identifiers. This execution is limited to specific maintenance commands and is only triggered after a confirmation step from the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-described requirements and formats them into task specifications.
  • Ingestion points: User descriptions provided in the initial step of the workflow.
  • Boundary markers: The skill uses distinctive header and footer markers (e.g., '--- PROPOSED ---') when presenting data for review.
  • Capability inventory: File system writing and execution of the mdtask CLI.
  • Sanitization: The workflow enforces a mandatory human-in-the-loop approval process, ensuring the user reviews and authorizes all generated content before it is saved or processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 03:51 AM
Security Audit — agent-trust-hub — mdtask-add