pp-help-scout

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs embedding a bearer token in a CLI command (help-scout-pp-cli auth set-token YOUR_TOKEN_HERE), which would require the agent/LLM to accept and output the secret verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The skill provides a read-only CLI for Help Scout and can fetch conversation/customer data by ID via commands like conversations get/conversations list, which would ingest insider-authored message text from the Help Scout inbox if the agent/runtime is used to query those records.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's setup/install steps execute remote code at runtime via Go installs (e.g., go install github.com/mvanhorn/printing-press-library/library/sales-and-crm/help-scout/cmd/help-scout-pp-cli@latest and go install github.com/mvanhorn/printing-press-library/library/sales-and-crm/help-scout/cmd/help-scout-pp-mcp@latest), which fetches and builds remote repository code required for the skill.