skill-finder

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

• Third-party content exposure detected (high risk: 0.80). The skill performs real-time searches of the public skills.sh site (via npx skills search and a WebFetch fallback to https://skills.sh/) and reads GitHub skill pages/repos, ingesting community-provided skill descriptions/metadata and thus exposing the agent to untrusted third-party content that it interprets as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly uses a runtime WebFetch to pull search results from https://skills.sh/?search={primary_keyword} (and more generally https://skills.sh/) and instructs the agent to "List matching skills..." using that fetched content, so external content is fetched at runtime and directly controls the agent's prompts.