strict-english
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is comprised solely of natural language instructions and configuration metadata. It does not include any scripts, dependencies, or network-enabled components.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided text for rewriting. While it lacks explicit delimiters for untrusted input or output sanitization, it has no tool-calling capabilities or file system permissions (explicitly restricted by the disable-model-invocation frontmatter), rendering the indirect injection surface non-exploitable.
Audit Metadata