super-translate

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to capture and forward user-provided parameters directly to another skill.
  • Ingestion points: User arguments including file paths, sections, or keywords handled by the forwarding contract in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions present in SKILL.md to separate user-provided data from the agent's internal logic.
  • Capability inventory: The skill itself performs no file system writes or network operations, delegating all functional logic to the 'translate' skill as described in SKILL.md.
  • Sanitization: User input is passed through to the downstream skill without validation, filtering, or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:03 PM
Security Audit — agent-trust-hub — super-translate