skills/wintree86/plan-task-fix/plan/Gen Agent Trust Hub

plan

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes 'git rev-parse --show-toplevel' to identify the project root directory, which is a standard procedure for project-aware development tools.
  • [EXTERNAL_DOWNLOADS]: The documentation references installation via 'npx skills add wintree86/plan-task-fix'. This is a vendor-owned resource belonging to the author 'wintree86' and is used to extend the suite's functionality.
  • [PROMPT_INJECTION]: The skill processes untrusted data when reading existing 'plan.md' files to summarize or update tasks. 1. Ingestion points: 'plan.md' files located via the document folder search order or CWD. 2. Boundary markers: None identified in the instruction logic to separate read file content from system instructions. 3. Capability inventory: 'Read', 'Edit', 'Write', 'Glob', and 'Grep' tools for file manipulation. 4. Sanitization: No explicit filtering or validation of existing markdown content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 11:30 PM