using-agent-skills
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and metadata. It contains no executable scripts, binaries, or logic that could be exploited for malicious purposes.
- [SAFE]: The instructions explicitly promote security best practices by incorporating a 'security-and-hardening' phase into the development lifecycle and requiring a security review for any changes involving untrusted input or data handling.
- [SAFE]: The skill includes anti-sycophancy measures (Behavior 3: Push Back When Warranted), which instructs the AI to challenge technically flawed human decisions, serving as a safeguard against accidental or intentional implementation of bad practices.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation was found in the provided files.
Audit Metadata