search
Warn
Audited by Snyk on Mar 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly includes "Web Search" and "Web Fetch" commands (e.g., "casedev search web" and "casedev search webfetch 'https://...') that fetch and ingest arbitrary public web pages and search results which the agent is expected to read and act on, exposing it to untrusted third‑party 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: 0.90). The casedev "webfetch" command fetches arbitrary URLs at runtime (e.g., https://example.com/ruling.html and https://casetext.com/case/example-v-example) and exposes a --context option that injects fetched page content into the agent/model context, so remote content can directly control prompts.
Audit Metadata