writing-standards
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The skill includes instructions for 'AI Pattern Elimination' (such as removing the phrase '~를 넘어'). These are stylistic constraints designed to improve content quality and do not attempt to bypass safety guardrails or override system-level instructions.
- Data Exposure & Exfiltration (SAFE): The skill references a local directory (.claude/docs/claude-code-docs/) for the purpose of citing official documentation. It does not contain instructions to transmit sensitive files or hardcoded credentials to external servers.
- Indirect Prompt Injection (SAFE): The skill defines a surface for processing external documentation which could theoretically be manipulated, though it is used here for legitimate citation purposes. 1. Ingestion points: Local documentation files in .claude/docs/claude-code-docs/ as specified in modules/citation-rules.md. 2. Boundary markers: Absent from the instruction set. 3. Capability inventory: The skill utilizes Read, Grep, and Glob tools to inspect file contents. 4. Sanitization: The skill emphasizes manual verification of URLs and facts but lacks programmatic sanitization of ingested content.
Audit Metadata