dialogue-polish
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text (dialogue and character descriptions), creating an attack surface where embedded instructions could potentially influence the agent's behavior.
- Ingestion points: The skill explicitly requests 'The dialogue' and 'Who the characters are' as input in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or guardrails to isolate the user-provided dialogue from the skill's operational instructions.
- Capability inventory: The skill does not use high-risk capabilities like arbitrary command execution or network requests; its primary external action is saving output to a connected notes app or tool.
- Sanitization: No sanitization or escaping of the user-provided text is performed before processing.
Audit Metadata