skill-creator
Warn
Audited by Snyk on Feb 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: 0.70). The skill's instructions explicitly show executing shell commands that inject external data into the agent prompt (e.g., "PR diff: !
gh pr diff" in SKILL.md), which pulls user-generated content from third-party GitHub PRs into the agent's context and could therefore carry indirect prompt-injection instructions that affect subsequent actions.
Audit Metadata