pp-jobber

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). In SKILL.md, the agent executes jobber-pp-cli <command> [subcommand] [args] --agent (Direct Use), where the user-provided free-text query is matched to a curated command via which "<capability in your own words>"/step 2 and then passed into the CLI, but the workflow does not describe ingesting any outsider-authored text feed (e.g., email/tickets/chat) without the agent first selecting a specific command and arguments.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's install instructions require fetching and running remote code to obtain the required CLI (so the skill may trigger runtime installs), specifically the Go module github.com/mvanhorn/printing-press-library/library/sales-and-crm/jobber/cmd/jobber-pp-cli@latest which is fetched/executed via go install.