octocode-brainstorming
Warn
Audited by Snyk on Aug 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Outsider-authored text is ingested at runtime via the web research path: the skill’s required workflow expands the user idea into queries and then fetches/search results through external web engines/workers (e.g., scripts/serper-search.mjs/tavily-search.mjs/exa-search.mjs and the host web tool), which can return free-text content authored by third parties.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata