annotate
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains only instructional text and references to local documentation files within the skill package (references/*.md). It does not perform any network operations, execute shell commands, or access sensitive system files.
- [PROMPT_INJECTION]: The skill processes user-supplied novel text, which is an inherent surface for indirect prompt injection. Given the lack of dangerous capabilities and its intended use for literary analysis, this presents no significant security risk.
- Ingestion points: User-provided novel chapters processed in SKILL.md.
- Boundary markers: No specific delimiters or 'ignore instructions' warnings are present in the workflow.
- Capability inventory: The skill provides analysis and suggests using other text-processing skills (expand, shuangdian, deslop, aidetect). No dangerous system access or code execution tools are requested.
- Sanitization: No input validation or escaping is implemented.
Audit Metadata