pachca-custom-properties

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly tells the agent to ask the user for a Pachca token and to include it verbatim in CLI commands or suggestions (e.g., using --token or pasting it into environment variables), requiring the LLM to handle/output a secret value directly.

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow runs npx -y @pachca/cli against Pachca API endpoints (e.g., GET /custom_properties), and the LLM is likely to ingest the API’s response body (outsider-authored free text from a third-party service) into its context via the tool output.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx -y @pachca/cli" at runtime, which fetches and executes remote code from the npm registry (e.g. https://registry.npmjs.org/@pachca/cli or https://www.npmjs.com/package/@pachca/cli), so it has a required external dependency that executes remote code.