ai-socratic-dialogue-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input through the
interrogation_topicfield and interpolates it directly into the prompt template inSKILL.md. There are no explicit boundary markers or sanitization steps to isolate this input from the instructions. An attacker could provide a topic designed to override the agent's formatting or persona. However, because the skill is restricted to text generation and lacks capabilities like network access, file system writes, or command execution, the risk is limited to output manipulation.
Audit Metadata