guodegang
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes user-supplied text for rewriting, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill takes user-provided phrases, paragraphs, and dialogues as primary input as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate user input from the skill's instructions.
- Capability inventory: The skill is limited to text generation and does not utilize high-risk tools such as shell execution, file system access, or network requests.
- Sanitization: The skill includes explicit instructions to filter out zero-width characters and noise from processed data, offering basic protection against content-based obfuscation.
Audit Metadata