punct-polish
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to transform user-provided text, which creates a natural surface for indirect prompt injection where instructions hidden in the input could influence agent behavior.
- Ingestion points: User-supplied text provided to the agent for punctuation correction and polishing.
- Boundary markers: While the skill provides instructions to protect code fences and URLs, it lacks robust boundary markers or explicit instructions for the agent to ignore directives contained within the text body.
- Capability inventory: Limited to text transformation, punctuation standardization, and vocabulary replacement.
- Sanitization: No mechanism is provided for sanitizing or filtering potential instructional content within the input data.
Audit Metadata