craft-prompt

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill is purely instructional and template-based.
  • [COMMAND_EXECUTION]: The skill mentions running standard development tools like git status, git diff, and git log to gather context for session handoff prompts. These are legitimate operations for a developer-oriented prompt-crafting skill and do not involve shell injection or privilege escalation.
  • [DATA_EXPOSURE]: The skill uses worktree-relative paths (e.g., src/auth.ts) as a best practice for prompt context, avoiding the exposure of absolute local system paths.
  • [REMOTE_CODE_EXECUTION]: There are no scripts, external downloads, or remote code execution patterns present in the skill files.
  • [OBFUSCATION]: A thorough scan for Base64, zero-width characters, homoglyphs, and encoded URLs returned no results.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 01:07 PM
Security Audit — agent-trust-hub — craft-prompt