mypy-to-ty
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
uvxandpre-committo manage packages and verify the migration. It also utilizes dynamic context injection (!find) to detect the presence of configuration files at skill load time. - [EXTERNAL_DOWNLOADS]: Fetches the
tyanduvtools from Astral (a well-known technology company) via theuvxpackage runner to perform migration and dependency management. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes user-controlled configuration files. \n
- Ingestion points: Reads content from
.pre-commit-config.yaml,pyproject.toml, andmypy.iniwithin the user repository. \n - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the file content as untrusted data or to ignore embedded instructions. \n
- Capability inventory: The skill is authorized to perform file modifications (
Write,Edit) and execute shell commands (uvx,pre-commit), which could be abused if malicious instructions are present in the configuration files. \n - Sanitization: No sanitization, validation, or escaping is performed on the ingested file data before processing.
Audit Metadata