factcheck

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires verifiers to fetch sources and "quote it verbatim" and write full findings (quotes) to files, which forces the LLM to include any secret strings present in fetched or pasted documents verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill reads an outsider-supplied document at runtime (via /factcheck <path | URL> → “Read the document (WebFetch if a URL; ask for a paste if it’s paywalled)”), and then extracts and quotes checkable claims from it into the agent’s LLM context for Step 1/2 verification.