prose-rhythm
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted text provided by the user or fetched from a manuscript.
- Ingestion points: Processes text pasted by the user or fetched from a manuscript via the Calliope MCP connector (writecalliope.ink).
- Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the processed text.
- Capability inventory: The skill is restricted to text analysis and feedback; it explicitly states it 'never writes or rewrites' and has no code execution or network exfiltration capabilities.
- Sanitization: No evidence of sanitization or filtering for embedded instructions in the ingested text was found.
Audit Metadata