launch-readiness-auditor

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime reads include “public access / pricing-page check (WebFetch, own site)” and “platform rules … published guidelines” (keyless public web content), which can ingest outsider-authored free text from fetched pages into the LLM context for R1/M1 scoring.

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 instructs it to fetch the runbook at runtime from https://raw.githubusercontent.com/aaron-he-zhu/aaron-marketing-skills/main/references/, and that fetched document is required and directly controls the auditor's scoring/instructions.