gitea-tea
Warn
Audited by Snyk on Feb 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: 0.90). The skill invokes commands that fetch and display external Gitea content (e.g., "tea issue 42", "tea pr 15", "tea issues list --repo owner/repo", "tea clone owner/repo") so the agent would ingest user-generated issues, PRs, comments and repository content from arbitrary/public Gitea instances, which are untrusted third‑party sources.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (medium risk: 0.60). The prompt explicitly instructs using sudo to install the tea binary (e.g., "sudo mv tea /usr/local/bin/"), which directs the agent to perform privilege-escalating system changes that modify machine state.
Audit Metadata