rust-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 and extracts documentation from public third‑party sites (e.g., docs.rs and any user-provided URLs via agent-browser/WebFetch) and then reads and incorporates that untrusted, user-authored content into generated skills, which could enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill issues runtime fetches (agent-browser/WebFetch and /create-llms-for-skills) to URLs such as https://docs.rs/{crate}/latest/{crate}/ and https://doc.rust-lang.org/... and uses the fetched documentation to generate llms.txt and SKILL.md which directly shape agent prompts/instructions.