apitally-cli

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

• Third-party content exposure detected (high risk: 0.90). The skill's Investigation Workflow and command reference (e.g., SKILL.md and references/commands.md) instruct the agent to run npx @apitally/cli request-logs and request-details against the public Apitally service, ingesting untrusted user-generated request/response bodies, headers, and application logs which the agent is expected to read and use to drive further actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs running "npx @apitally/cli" which will fetch and execute the remote npm package (e.g. https://www.npmjs.com/package/@apitally/cli), so it relies on externally downloaded code that is executed at runtime.