conference-talk-builder
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- NO_CODE (SAFE): The skill contains only Markdown instructions and local reference files. No executable code or scripts are present.
- Indirect Prompt Injection (INFO): The skill processes user-provided talk ideas and content. 1. Ingestion points: User input for talk title, topic, and brain dump in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: None; the skill performs text generation only and lacks tool calls or file system write access. 4. Sanitization: None. Severity is INFO as there are no exploitable side effects.
- Data Exposure (SAFE): No access to sensitive files, environment variables, or external network endpoints was detected.
Audit Metadata