red-pen
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided prose as its primary function, which creates an inherent attack surface for indirect prompt injection. However, since the skill has no access to sensitive capabilities like file writing, network operations, or shell execution, this surface does not present a security risk.
- Ingestion points: User-supplied prose text via chat interaction (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters for separating user input from the editorial prompt.
- Capability inventory: Restricted to chat-based text output; no subprocess, network, or file-system capabilities detected.
- Sanitization: Input is processed as raw text without specific sanitization or escaping mechanisms.
Audit Metadata