addon-llm-ancient-greek-translation
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process user-supplied text for translation, which presents a surface for indirect prompt injection where malicious instructions could be embedded in the source data. \n
- Ingestion points: Untrusted data enters the agent context through the sourceText field defined in src/lib/llm/ancient-greek.ts. \n
- Boundary markers: No specific delimiters or "ignore previous instructions" markers are defined in the provided template files. \n
- Capability inventory: The skill logic does not utilize high-risk capabilities such as arbitrary code execution, file system modifications, or network-bound subprocess calls. \n
- Sanitization: The skill includes an AncientGreekResponseSchema using Zod to enforce that LLM outputs strictly adhere to the expected translation object structure. \n- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the zod package, a widely recognized and well-known library for schema validation, from the official registry. \n- [COMMAND_EXECUTION]: The integration workflow suggests using standard development tools and commands, including bun run lint, bun run build, test for file verification, and ripgrep (rg) for searching source files.
Audit Metadata