handbook-writing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The instructions focus purely on writing style and tone. No commands were found that attempt to override AI safety guidelines or extract system prompts.
- Data Exposure & Exfiltration (SAFE): There are no hardcoded credentials, sensitive file paths, or network-enabled commands (like curl or fetch) present in the skill.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not include any scripts, package manifests, or remote download commands.
- Indirect Prompt Injection (SAFE): Although the skill is intended to process user-provided documentation, it lacks any high-risk capabilities such as file-writing, network access, or shell execution, neutralizing the risk of indirect injection.
- Persistence & Privilege Escalation (SAFE): No commands related to system configuration, account creation, or permission modification were detected.
Audit Metadata