ai-content-verifier

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly shows commands that pass the raw input text on the command line (python scripts/verifier.py --text "<input_text>") and requires the report to quote claims/resources verbatim, so any secrets in user-provided text or URLs would be echoed directly by the LLM — creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The skill ingests outsider-authored free text directly via “Direct paste” or a user-supplied “URL” (webfetch), then extracts and verifies any URLs/DOIs/packages found in that text (including attacker-provided content) using python scripts/verifier.py --text "<input_text>" / webfetch/batch HEAD checks.