soia-pkm-translate

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local Python scripts included in the package (scripts/chunk_markdown.py, scripts/resolve_config.py) to handle document chunking and configuration management. These scripts use standard Python libraries and do not perform network requests.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads and processes untrusted user-provided files for translation.
  • Ingestion points: Reads arbitrary local files provided by the user for translation tasks.
  • Boundary markers: Absent. The skill does not wrap the source text in delimiters to prevent the agent from obeying instructions embedded within the text.
  • Capability inventory: The skill performs file system read/write operations and local Python script execution.
  • Sanitization: Absent. No filtering or escaping is applied to the source text before it is processed by the language model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 03:44 PM
Security Audit — agent-trust-hub — soia-pkm-translate