best-practices-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill is declarative and focuses on best practices for session management and verification.\n- [NO_CODE] (INFO): The skill file is composed of Markdown instructions only. There are no scripts, binaries, or configuration files that could trigger command execution or runtime vulnerabilities.\n- [PROMPT_INJECTION] (SAFE): The content does not attempt to bypass safety filters, override system constraints, or extract internal instructions; rather, it provides heuristic-based self-correction guidelines.\n- [DATA_EXFILTRATION] (SAFE): No sensitive file paths, credential markers, or network-capable commands (e.g., curl, wget) are present in the skill definition.
Audit Metadata