streamer-bait-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- EXTERNAL_DOWNLOADS (SAFE): The skill references documentation from high-reputation sources including Microsoft (Trusted Organization), Twitch, and OBS. These are provided for developer reference and do not involve remote code execution or automated downloads.
- INDIRECT_PROMPT_INJECTION (LOW): This skill defines a framework for analyzing user-supplied source code against streamability patterns. [Evidence Chain] 1. Ingestion points: User-provided game scripts (.js, .cs, .css, .gd); 2. Boundary markers: Absent; 3. Capability inventory: None (the skill has no access to shell, network, or file-write capabilities); 4. Sanitization: None. Because the skill lacks any dangerous capabilities, the ingestion of untrusted code for analysis represents a minimal risk.
- PROMPT_INJECTION (SAFE): No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected within the skill's instructions or reference files.
- DATA_EXPOSURE (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were identified.
Audit Metadata