technical-blog-writing
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external research data through the
exa/searchtool, creating a surface for potential indirect prompt injection from web content. This is a standard risk for research-oriented skills and is mitigated by the skill's specific focus on writing structure. - [DYNAMIC_EXECUTION]: Provides a static Python script template for generating benchmark charts using
matplotlibvia a CLI tool. The script is used for data visualization and does not incorporate unvalidated external code. - [EXTERNAL_DOWNLOADS]: References official installation documentation and additional writing-related skills from the
inference-shGitHub repository. These sources are part of the platform's infrastructure and are considered safe for the intended use-case.
Audit Metadata