synthesis-writing-craft

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown-based instructional content and references to writing-craft books. No executable scripts, binaries, or configuration files that could pose a security risk were found.
  • [NO_CODE]: The skill does not define any automated actions, tool calls, or background processes. It serves as a behavioral guideline for the LLM during text generation tasks.
  • [EXTERNAL_DOWNLOADS]: Mentions of the author's website (synthesiswriting.org) and the source repository on GitHub (github.com/synthesisengineering/synthesis-skills) are informational and consistent with the vendor's identity. There are no automated downloads or remote code executions.
  • [PROMPT_INJECTION]: The instructions are focused on writing style (e.g., 'Cut adverbs', 'Vary sentence length'). There are no attempts to override system safety prompts, bypass restrictions, or implement 'jailbreak' patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 09:44 AM
Security Audit — agent-trust-hub — synthesis-writing-craft