pflow-task-finish

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs its intended functions (git operations and task management) without any malicious patterns detected.
  • [COMMAND_EXECUTION]: The script executes git and mdtodo commands. All user-supplied or data-derived arguments (like commit messages, slugs, and branch names) are properly quoted or processed through a slugification function before execution.
  • [EXTERNAL_DOWNLOADS]: The skill depends on a library script (git-lib.sh) from a sibling skill (pflow-commit). This is a standard dependency within the agent skill ecosystem and does not involve downloading code from untrusted remote sources.
  • [DATA_EXFILTRATION]: The skill performs git push operations to move code to remote repositories. This is the primary purpose of the skill and does not involve unauthorized data movement.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 07:19 PM
Security Audit — agent-trust-hub — pflow-task-finish