writing-for-agents
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and YAML metadata intended to guide the writing of agent-facing content. It does not include any executable scripts, shell commands, or tool definitions.\n- [SAFE]: There is no evidence of credential exposure, data exfiltration, or obfuscation. The reference to an external GitHub repository in the changelog is for historical provenance and does not involve runtime execution.\n- [SAFE]: The skill explicitly includes defensive instructions, such as anti-patterns that warn the agent against treating external content or tool outputs as trusted instructions.
Audit Metadata