tasks-generator

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands for Git workflow management, including git fetch, git pull, git commit, and git push to synchronize changes with the remote repository. It also optionally executes a local Python script scripts/update_readme_ideas_index.py if it exists in the repository structure.
  • [EXTERNAL_DOWNLOADS]: Network operations are limited to standard Git synchronization tasks with the user's established remote origin.
  • [DATA_EXFILTRATION]: The skill reads project-specific documentation (e.g., prd.md, tad.md) and local configuration markers (e.g., ~/.config/ideas-root.txt) to extract requirements and resolve project paths. No data is sent to unauthorized external domains.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from PRD files, which constitutes a surface for indirect prompt injection. This is a low-severity risk inherent to the skill's primary function of document analysis and task generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 05:45 PM
Security Audit — agent-trust-hub — tasks-generator