idea-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [No Code] (SAFE): The skill consists entirely of natural language instructions and lacks any executable scripts, shell commands, or external dependencies.
- [Prompt Injection] (SAFE): No patterns for instruction overrides, system prompt extraction, or safety filter bypasses were detected.
- [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive file paths, environment variables, or hardcoded credentials.
- [Indirect Prompt Injection] (LOW): While the skill ingests untrusted user input regarding business interests, it lacks the capabilities (network, file system, or code execution) required for an exploit to cause side effects.
- Ingestion points: User interests provided in the chat context.
- Boundary markers: Absent.
- Capability inventory: None; the skill only generates text output.
- Sanitization: Absent, though unnecessary given the lack of actionable tools.
Audit Metadata