auditing-skills

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

• Third-party content exposure detected (high risk: 1.00). This skill's audit workflow explicitly tells the agent to fetch and read audit pages and detailed findings from public sites (e.g., skills.sh individual skill pages and security/{auditor} detail URLs, and tessl.io registry/skill pages), which are untrusted third‑party web content that the agent is expected to interpret and that can materially influence its remediation and follow‑up actions.