advisory-mining

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

• Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly instructs the agent to fetch and read public GitHub advisories via the GitHub Advisory API (gh api ...), retrieve patch diffs from public repositories (git show / git diff), and query the NVD API / grep.app, so it ingests untrusted, user-generated third-party content that the agent must interpret and act on.