writing-great-skills
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill serves as a reference guide for skill development best practices. Analysis of the content reveals no malicious intent or security vulnerabilities.
- [NO_CODE]: The files consist entirely of Markdown text. There are no scripts, configuration files that execute commands, or binary files included.
- [PROMPT_INJECTION]: The instructions do not attempt to override agent behavior or extract system prompts. The 'Failure modes' section specifically warns against negative prompting ('Negation') as a common pitfall, which is a standard safety-aligned prompting principle.
- [DATA_EXFILTRATION]: No network access or sensitive file operations are performed. The skill references a local glossary file but does not access credentials or environment variables.
- [OBFUSCATION]: The text is clear and readable with no evidence of Base64 encoding, zero-width characters, or homoglyph substitution.
Audit Metadata