gtm-scorecard
Warn
Audited by Snyk on Jul 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent at runtime to fetch job-description and search results from external APIs which directly feed the model's evidence and outputs (e.g., ATS APIs like https://api.ashbyhq.com/posting-api/job-board/[slug]?includeCompensation=true and Exa endpoints such as https://api.exa.ai/contents and https://api.exa.ai/search), so these runtime-fetches can directly control the agent's prompts/evidence.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata