skills/xberg-io/tree-sitter-language-pack/tree-sitter-language-pack-detecting-languages/Gen Agent Trust Hub
tree-sitter-language-pack-detecting-languages
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides documentation for executing the
ts-packCLI tool, which is a utility provided by the vendor (xberg-io) for parsing and processing code files. - [INDIRECT_PROMPT_INJECTION]: The skill documents methods for processing raw source code content via functions like
detect_language_from_content. This identifies a surface where the agent may ingest untrusted data from external code snippets for classification. - Ingestion points: SDK functions
detect_language_from_contentand CLI commandsparse/processin SKILL.md. - Boundary markers: None mentioned in the usage documentation.
- Capability inventory: The documented tool is designed for language detection and metadata extraction. No arbitrary execution of code content is indicated in the instructions.
- Sanitization: No specific sanitization or filtering of input content is described in the provided examples.
Audit Metadata