translate-skill

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute local scripts and Git commands to validate translation integrity and synchronization.
  • Evidence: node scripts/check-translation.mjs
  • Evidence: node scripts/audit-english.mjs
  • Evidence: git diff --check
  • [PROMPT_INJECTION]: The skill defines a workflow for processing untrusted data from an external upstream repository, creating a surface for indirect prompt injection.
  • Ingestion points: Content from mattpocock/skills (SKILL.md)
  • Boundary markers: Instructions to protect behavior-critical spans and preserve Markdown structural elements.
  • Capability inventory: Command execution via Node.js and Git.
  • Sanitization: Explicit requirements to preserve identifiers, frontmatter keys, and code blocks unchanged.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 02:30 PM
Security Audit — agent-trust-hub — translate-skill