flow-state-condition-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts several user-controlled inputs that are interpolated directly into the system prompt, creating a potential surface for indirect prompt injection.
- Ingestion points: Inputs for
lesson_activity,student_profiles, and other context fields are mapped to placeholders in the prompt section ofSKILL.md. - Boundary markers: The prompt lacks explicit delimiters or instructions for the model to treat the interpolated content as data rather than instructions.
- Capability inventory: The skill is limited to text generation; it does not utilize any tools for file system access, network communication, or shell command execution.
- Sanitization: No input filtering or validation mechanisms are implemented within the skill definition.
- [NO_CODE]: The skill is a template-based prompt and does not contain any executable scripts, binaries, or logic that could be exploited for traditional remote code execution.
Audit Metadata