rust-dependency-audit

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md's "CRITICAL: Web-Verify Before Upgrade Decisions" explicitly instructs the agent to WebFetch the public crates.io API, perform WebSearches for advisories, and even fallback to a firecrawl scrape of crates.io pages—all open/public third‑party content the agent is expected to read and use to make upgrade/ignore decisions, so it can influence behavior and 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 explicitly performs runtime WebFetch calls to the crates.io API (e.g. https://crates.io/api/v1/crates/{crate_name} and https://crates.io/api/v1/crates/{crate_name}/{version}/dependencies) and a fallback scraper (http://bigblack:3002/v1/scrape) and then uses the fetched content to form prompts/upgrade decisions, so external content directly controls agent instructions at runtime.