deep-research

Warn

Audited by Snyk on Apr 7, 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's workflow and agent delegation explicitly instruct the deep-researcher agent to use EXA web_search / get_code_context tools to gather web content (see SKILL.md "Agent Delegation" and WORKFLOW.md step 3b "Invoke deep-researcher agent" with "web_search_exa"), and the resulting sources/URLs are stored in metadata, so untrusted public web content is fetched and can influence caching, refresh, and promotion actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 09:30 PM
Issues
1