searching-sourcegraph
Warn
Audited by Snyk on Jun 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: 0.75). The skill’s workflow uses Sourcegraph search/navigation tools (e.g.,
nls_search,keyword_search,read_file) that can fetch and ingest repository file contents authored by third parties (outsider code/docs) into the agent’s LLM context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata