humanize-chinese
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a text processing tool which inherently involves processing untrusted user-provided data.
- Ingestion points: Processes user-supplied text files (such as text.txt or paper.txt) and manual inputs through analytical and rewriting workflows.
- Boundary markers: Absent; the instructions do not implement specific delimiters (like XML tags or block quotes) to isolate external content from the agent's instructions.
- Capability inventory: References file system operations (read/write) and command execution via local Python scripts if available.
- Sanitization: Absent; the workflow does not explicitly describe validation or sanitization of the input text before processing or passing it to command-line tools.
Audit Metadata