ss-component
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses user-provided descriptions via the $ARGUMENTS variable to guide its code generation process without applying sanitization or boundary markers. This creates an attack surface for indirect prompt injection, where malicious instructions inside a component description could potentially influence the agent's behavior. \n
- Ingestion points: SKILL.md (via $ARGUMENTS variable). \n
- Boundary markers: None; user input is interpolated directly into the task instructions. \n
- Capability inventory: The skill utilizes Write, Edit, and Bash tools to perform project modifications. \n
- Sanitization: No explicit sanitization, filtering, or validation is performed on the user-provided arguments.
Audit Metadata