discussion-protocol-selector
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a purely instructional tool that operates within the agent's text generation capabilities. It contains no scripts, binaries, or commands that interact with the host system or external networks.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it interpolates user-provided text into its internal prompt without using protective delimiters. However, this is categorized as safe because the skill has no access to tools or sensitive data that could be exploited.
- Ingestion points: The input fields discussion_purpose, topic_or_question, and student_level in SKILL.md.
- Boundary markers: Absent; user inputs are placed directly into the prose of the prompt.
- Capability inventory: None. The skill does not have allowed-tools or any referenced scripts with system capabilities.
- Sanitization: None present.
Audit Metadata