technical-article
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a purely instructional framework for technical writing and does not contain any executable code, network operations, or hardcoded credentials.\n- [SAFE]: External references link to official documentation from trusted organizations and well-known services.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes Markdown files for review and revision, which constitutes an ingestion surface.\n
- Ingestion points: Markdown files located in
content/articles/,docs/articles/, andarticles/directories.\n - Boundary markers: The instructions do not define specific markers to delimit user-provided article content.\n
- Capability inventory: The skill involves reading and writing Markdown files but lacks network or system-level capabilities.\n
- Sanitization: No explicit sanitization of external content is performed. However, the requirement for the agent to enforce a formal, structured style guide mitigates the risk of executing embedded instructions.
Audit Metadata