dot-ai-worktree-prd

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard Git and shell commands (git worktree add, git submodule update, ls, grep) to automate workspace management. These operations are restricted to the local repository context and follow common development workflows.
  • [PROMPT_INJECTION]: The skill demonstrates best practices for handling untrusted data from external files (PRD documents).
  • Ingestion points: The agent reads PRD titles from files located in the prds/ directory (SKILL.md, Step 2).
  • Boundary markers: No explicit boundary markers are present in the documentation for the file content.
  • Capability inventory: The skill possesses the ability to execute shell commands and modify the local file system through Git worktree operations.
  • Sanitization: The skill mitigates potential command injection and indirect prompt injection by providing explicit instructions in Step 3 to sanitize derived strings (converting to lowercase, replacing spaces with hyphens, and removing all special characters except hyphens and dots) before using them as arguments in shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 05:59 PM
Security Audit — agent-trust-hub — dot-ai-worktree-prd