fact-check

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires agents to perform WebFetch/WebSearch/gh lookups and ingest content from external URLs as "Valid evidence" (see "Evidence Rules" and "Verification Agent Spawning"), meaning untrusted public web content will be read and used to drive verdicts and follow-up actions, which could carry indirect prompt-injection instructions.