pagetranslate-document-translator
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the PageTranslate API. These commands are used for uploading files, starting translation jobs, polling for status, and downloading results. - [DATA_EXFILTRATION]: The skill transmits user-selected document files to
api.pagetranslate.ai. As this is the primary functionality of a translation skill and targets the official vendor domain, it is considered a legitimate data transfer rather than malicious exfiltration. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted document formats (DOCX, PDF, etc.) which provides a potential surface for indirect prompt injection attacks.
- Ingestion points: Document files provided by the user for translation (referenced in
SKILL.md). - Boundary markers: None specified for the content of the documents being processed.
- Capability inventory: Shell command execution via
curland network access (referenced inSKILL.md). - Sanitization: No explicit sanitization or filtering of document content is mentioned before processing.
Audit Metadata