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 ingests public documentation from docs.rs, doc.rust-lang.org, and arbitrary user-provided URLs via the /create-llms-for-skills command, meaning the agent will read and process untrusted third-party (often user-generated) web content that could carry indirect prompt injections.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs the /create-llms-for-skills command at runtime to fetch documentation from URLs such as https://docs.rs/{crate}/latest/{crate}/ and https://doc.rust-lang.org/... which are then used to generate llms.txt that directly controls the agent's prompts/instructions, so these external docs are a runtime dependency that can control behavior.