plan-security-audit
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a controlled security audit workflow that focuses on identification and planning rather than execution, which minimizes risk to the target system.
- [INDIRECT_PROMPT_INJECTION]: While the skill analyzes untrusted source code and configuration files—a surface for indirect prompt injection—it is well-mitigated by its primary design. The 'plan-only' mandate and 'no-destructive-testing' rules prevent the agent from performing unauthorized actions even if malicious instructions were encountered in the audited code. Additionally, the explicit rule against echoing secret values protects against data exfiltration attempts via the analysis output.
Audit Metadata