article-writer

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process external data sources.
  • Ingestion points: The workflow involves reading project context files (e.g., CLAUDE.md, AGENTS.md) and user-supplied source materials.
  • Boundary markers: There are no explicit delimiters or protective instructions used when processing this external content.
  • Capability inventory: Across the SKILL.md and its referenced tools, capabilities are limited to text generation, formatting, and web searching; no high-risk file system modifications or direct network exfiltration paths are present.
  • Sanitization: The skill does not define methods for sanitizing or escaping the data read from project files or source materials.
  • [NO_CODE]: The skill consists entirely of markdown instructions and templates without any executable code, scripts, or package dependencies, significantly reducing the direct attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 03:34 PM
Security Audit — agent-trust-hub — article-writer