cms-article-restructure
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a legitimate workflow for article restructuring within a CMS environment. No malicious patterns such as data exfiltration, unauthorized command execution, or obfuscation were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content (article paragraphs) from a CMS. This presents a theoretical surface for indirect prompt injection if the processed content contains instructions meant to subvert the agent's behavior. However, the skill mitigates this risk by requiring a 'dry-run' phase and explicit user approval before applying any mutations to the data.
Audit Metadata