infosec-engineer
Warn
Audited by Snyk on Apr 13, 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's integrations doc and workflow (references/integrations.md and SKILL.md) instruct the agent to connect to MCP servers and directly read repositories, issues, pipelines, and registry URLs (e.g., GitHub, GitLab, Jira, and the MCP Registry), which are open/public, user-generated sources the agent will ingest and act on—allowing untrusted third-party content to influence tool use and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata