skill-scout
Warn
Audited by Snyk on Jun 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow includes “Search Remote Sources” via GitHub/web search and then “Vet External Matches” by reading external
SKILL.mdfrontmatter/instructions, which can ingest outsider-authored free text from public web/GitHub repositories into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata