tree-sitter
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: 0.80). The skill's Workflow 1 explicitly instructs installing parsers by git-cloning grammars from public GitHub repos (e.g., https://github.com/tree-sitter/tree-sitter-<언어> and https://github.com/tree-sitter-grammars/...), which are untrusted third-party sources whose grammar code is loaded by tree-sitter and can change parsing results that the agent reads and acts on.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill's on-demand setup instructs cloning remote grammars at runtime (e.g. git clone --depth 1 https://github.com/tree-sitter/tree-sitter-<언어> and https://github.com/tree-sitter-grammars/tree-sitter-<언어>), which fetches third-party grammar code that will be loaded/executed by the tree-sitter CLI as a required dependency.
Audit Metadata