Skills
skills/anand-testcompare/scripts-prompts-config/workos-agent-access/Gen Agent Trust Hub

workos-agent-access

Warn

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The script scripts/issue-sealed-session.mjs handles sensitive credentials, including the WorkOS API key and user passwords, by passing them as a JSON string argument to a spawned Node.js process. This practice makes the secrets visible in the system's process table to other users or system monitoring tools.
  • [COMMAND_EXECUTION]: The script scripts/issue-sealed-session.mjs employs dynamic code execution by generating a JavaScript string at runtime and executing it via the node -e command.
  • [EXTERNAL_DOWNLOADS]: The skill performs automated installation of the @workos-inc/node SDK from the NPM registry during execution if it is not already present in the local directory.
  • [PROMPT_INJECTION]: The skill represents an indirect prompt injection surface as it ingests project configuration data from files like convex.json to drive automation. 1. Ingestion points: Reads local configuration files as specified in playbook.md. 2. Boundary markers: None. 3. Capability inventory: Subprocess execution and network requests in scripts/. 4. Sanitization: None.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 20, 2026, 07:06 AM