reverse-engineer-anything

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

• Third-party content exposure detected (low risk: 0.10). The required workflow involves reading firmware analysis and web network capture documentation from GitHub repositories, which is low risk as it involves fetching selected documentation URLs.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to run npx -y rea-agents@latest as a package acquisition command when the rea CLI is missing, introducing an unverifiable third-party operational dependency on the npm registry.