open-targets-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to ask the user for an 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 in executed commands.

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

• Third-party content exposure detected (low risk: 0.10). The required workflow queries the Valyu search API to retrieve third-party dataset content and search results containing external-facing drug-target records, which exposes the agent to outsider-authored free text via search retrieval.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes runtime HTTP requests to the Valyu API (https://api.valyu.ai/v1) for search functionality, which constitutes a recognized third-party API service dependency with common/reputable unofficial provenance.