clerk-token-ops
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local scripts
scripts/Set-ClerkToken.ps1andscripts/get_clerk_token.pyto automate the generation and export of Clerk JWT tokens. - [DATA_EXFILTRATION]: The skill requires access to
.env.local, which is documented to contain sensitive credentials includingCLERK_SECRET_KEYandCLERK_PEM_PUBLIC_KEY. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing output from local scripts without delimiters. 1. Ingestion points: Output from local scripts
scripts/Set-ClerkToken.ps1andscripts/get_clerk_token.py. 2. Boundary markers: Absent. 3. Capability inventory: PowerShell and Python script execution, and local file system access. 4. Sanitization: Absent.
Audit Metadata