cuda-webdoc-search
Warn
Audited by Snyk on Apr 21, 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 actively fetches and parses public documentation pages (e.g., inventory_urls in registry.toml pointing to docs.nvidia.com and the SKILL.md examples), using fetchers.fetch_soup / get.fetch_content (used by get_sphinx_groups, get_doxygen_members, and get_doc) to ingest third‑party HTML/objects.inv content which the tool interprets to build search results and drive subsequent actions, so untrusted remote content can influence the agent's behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata