patents-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to ask the user for their API key and then pass it directly as a command-line argument (scripts/search setup <api-key>), causing the secret to pass through the LLM context and appear verbatim in generated commands.

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

• Third-party content exposure detected (low risk: 0.10). The skill searches global patent data via the Valyu API, ingesting search results which contain outsider-authored patent text (low risk as the agent must actively query).