Project Tracking

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses basic shell commands like ls, mkdir, mv, and touch to manage the project workspace as described in references/workflows.md. These commands are standard for file organization within the docs/workspace/ directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes markdown files from the workspace directory which serve as context for the agent. While these files are ingestion points for untrusted data, the skill's capabilities are limited to local file management.
  • Ingestion points: Markdown files within docs/workspace/initiatives/, docs/workspace/ideas/, and docs/workspace/todos/.
  • Boundary markers: The templates do not include specific delimiters or instructions to ignore embedded commands, though the workflows are purely organizational.
  • Capability inventory: The agent performs file read, write, move, and directory listing operations using standard CLI tools.
  • Sanitization: No explicit content sanitization is performed on the tracked documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 04:11 AM