skills/xberg-io/tree-sitter-language-pack/tree-sitter-language-pack-parsing-source/Gen Agent Trust Hub
tree-sitter-language-pack-parsing-source
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
ts-packutility is configured to automatically download required tree-sitter parser libraries from remote sources upon their first use. These libraries are cached locally to support subsequent parsing operations for the same language. - [DYNAMIC_EXECUTION]: The tool dynamically loads these external parser libraries at runtime to perform its core function of syntax analysis and tree generation.
- [INDIRECT_PROMPT_INJECTION]: This skill defines a capability for the agent to ingest and analyze untrusted source code provided by users or external files, which represents a potential indirect prompt injection surface.
- Ingestion points: Source code files passed to
ts-pack parseor content provided via stdin. - Boundary markers: None; the tool processes the full content of the provided input.
- Capability inventory: The
ts-packtool executes shell commands, reads local files, and performs network downloads for its dependencies. - Sanitization: The skill does not specify any sanitization or validation steps for the input source code before it is parsed.
Audit Metadata