go-package-skill-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches package documentation from the public site https://pkg.go.dev/ and extracts overviews and official examples (public, user-maintained repository content), which the agent reads and interprets as part of its workflow, exposing it to untrusted third-party content.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches package documentation at runtime from https://pkg.go.dev/ and injects the fetched overview/examples into generated SKILL.md, meaning externally fetched content would directly control the agent's produced prompts/instructions.