writing-skills
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The analyzed skill consists entirely of instructional Markdown and Graphviz documentation files. It contains no executable code, scripts, or commands that interact with the host filesystem, environment variables, or network.
- [PROMPT_INJECTION]: The skill includes a reference file, persuasion-principles.md, which discusses psychological techniques (like Authority and Social Proof) to ensure AI agents follow strict development protocols (e.g., TDD). While these methods are analogous to instruction framing, they are used here purely for instructional clarity and discipline enforcement rather than attempting to bypass safety filters or ignore system guidelines.
- [EXTERNAL_DOWNLOADS]: The documentation references several well-known and trusted third-party libraries, such as pdfplumber, pypdf, and docx-js, as examples for processing various file formats. These references point to standard ecosystem tools and do not involve downloading or executing code from untrusted remote sources.
- [DATA_EXFILTRATION]: No patterns for data exfiltration or unauthorized file access were identified. The skill correctly references standard local directories intended for agent skill storage.
Audit Metadata