clinical-trials-search
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for their Valyu API key and then run a shell command embedding that key as a direct command-line argument (scripts/search setup ), which requires including the secret verbatim in output/commands.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill queries and returns full records from the public ClinicalTrials.gov database via the Valyu search API (see "Search the complete ClinicalTrials.gov database" and the returned "results[].content" and "results[].url" fields), so the agent ingests and interprets untrusted public third-party content.
Audit Metadata