drug-discovery-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly tells the agent to ask the user for their Valyu API key and run a command embedding that key (scripts/search setup <api-key>), which requires the LLM to output the secret verbatim (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md describes querying Valyu's /search API and returning full-text results aggregated from public third‑party sources (ChEMBL, DrugBank, FDA drug labels, Open Targets — see "Search across all major drug discovery databases" and the includedSources examples), so the agent ingests untrusted public web content that can influence downstream decisions.