ko-tech-writer

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute ripgrep (rg) and sed for identifying linguistic patterns, such as translationese or improper punctuation, in markdown files. It also executes internal scripts like scripts/test_ko_tech_writer_lanes.sh to calibrate its analysis engine. These operations are scoped to the skill's primary function as a documentation auditor.- [EXTERNAL_DOWNLOADS]: The WebFetch tool is utilized to retrieve technical blog samples from external URLs provided by the user. This data is used to calibrate the agent's tone and style to match the target publication venue.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from user-provided documents and external websites, creating an indirect prompt injection surface. Ingestion points: Technical blog samples (via WebFetch) and user-provided markdown files (via Read). Boundary markers: None are explicitly defined in the skill instructions. Capability inventory: Access to Bash, Edit, Write, WebFetch, and Read tools. Sanitization: No specific sanitization of external text is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:24 PM