Caveat verdict
workshub
Official WorksHub MCP skill for hiring human workers via API using a user-provided API key; all network calls go to workshub.ai and permissions are explicitly declared and scoped.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (3)
Possible hardcoded credential
SKILL.md · code · API_KEY="your_api_key_here
Popular HTTP library — network access
SKILL.md · code · axios
Accesses sensitive environment variables
bridge.js · prose · downgraded · process.env.WORKSHUB_API_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.