qr-decoder

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly parses and outputs sensitive fields like WiFi passwords and vCard contact data (e.g., "Password: password123"), which requires the LLM to include secret values verbatim in its output, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly supports downloading images from arbitrary web addresses (see "From URL" examples and the --url URL option in SKILL.md) and decodes untrusted, user-generated QR payloads (URLs, text, vCards, WiFi strings) that the agent is expected to parse and could materially influence subsequent actions or decisions.