agent-md-advisor
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely instructional and promotes security-conscious documentation practices. No malicious patterns, such as data exfiltration or unauthorized command execution, were detected.
- [NO_CODE]: Analysis of the skill's contents reveals only Markdown (.md) and YAML (.yaml) files. There are no executable scripts (Python, Node.js, Shell, etc.) included in the package.
- [PROMPT_INJECTION]: The skill does not contain instructions that attempt to override safety filters or bypass core agent guidelines. On the contrary, it provides a 'Review Rubric' that explicitly flags 'persona prompts' as low-signal and encourages 'technical briefs' instead.
- [CREDENTIALS_UNSAFE]: The skill includes explicit 'Gotchas' and rules in both its templates and best practices documents that forbid the inclusion of actual secrets, tokens, or credentials. It provides guidance on using environment variables and secret managers correctly.
Audit Metadata