create-rule
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow for the agent to generate persistent rule files based on conversation context and user input, establishing an indirect prompt injection surface.\n
- Ingestion points: User requirements and previous conversation context as specified in SKILL.md.\n
- Boundary markers: The skill lacks instructions for using delimiters or explicit markers to isolate untrusted input within the generated rules.\n
- Capability inventory: The skill guides the agent's file-writing capabilities specifically for the .cursor/rules/ directory.\n
- Sanitization: No input validation or sanitization procedures are defined to screen context before it is persisted in the rule files.
Audit Metadata