content-quality-auditor

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow allows fetching and extracting arbitrary user-provided URLs at runtime (“web crawler” / “firecrawl scrape returns rendered page as LLM-ready markdown”), which is outsider-authored free text that the agent then ingests into the LLM context for the audit.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's standalone-install fallback explicitly fetches the authoritative runbook at runtime from https://raw.githubusercontent.com/aaron-he-zhu/aaron-marketing-skills/main/references/, and that fetched runbook directly controls auditing instructions (the skill states "Do not score without the runbook"), so this is a required external instruction dependency.