add-integration
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's Step 3 explicitly performs WebSearch and WebFetch of public API documentation (official docs / web pages) and parses those third-party pages to discover and present endpoints, exposing the agent to untrusted open-web content that could carry indirect prompt-injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly performs runtime WebSearch/WebFetch on the discovered official API documentation URL (referenced in the skill as {api_docs_url}) and injects parsed endpoint and authentication instructions from that remote doc into prompts and generated project files, so the fetched external docs directly control the agent's prompts and output.
Audit Metadata