readme-i18n
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
uvtool to execute a project-local Python scriptscripts/count_mcp_tools.pywith the--update-docsflag. This is used for keeping tool counts synchronized within the documentation. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it reads and processes the content of
README.mdfor translation. - Ingestion points: Content is ingested from
README.mdand through direct user input for translation. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The agent can write to local Markdown files and execute a specific local Python script.
- Sanitization: There is no evidence of sanitization or filtering of the source content prior to translation or synchronization.
Audit Metadata