skills/terminalskills/skills/unkey/Gen Agent Trust Hub

unkey

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install @unkey/api via npm. This is the official client library for Unkey, a well-known API management service. The reference is documented neutrally as a standard dependency for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The provided authentication middleware processes untrusted data from incoming request headers.
  • Ingestion points: The authMiddleware function in SKILL.md ingests data from the Authorization header of a Request object.
  • Boundary markers: None present; the skill treats the header content as a literal token value.
  • Capability inventory: The skill uses the @unkey/api library to perform network-based key verification. No file system writes, subprocess execution, or shell access capabilities are present in the provided scripts.
  • Sanitization: The input is extracted from the header and passed directly to the verifyKey function without additional sanitization or filtering beyond standard string manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 04:30 PM
Security Audit — agent-trust-hub — unkey