anibon-talk-stream
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions are consistent with its stated purpose of summarizing and timestamping video content for the streamer Boat from Anibon Official. No malicious code, obfuscation, or unauthorized network activity was detected.- [PROMPT_INJECTION]: The skill processes external video transcripts, which is an ingestion point for untrusted data. While this creates a potential surface for indirect prompt injection, the skill's capabilities are focused on transcription and timestamping. 1. Ingestion points: Transcript segments provided to the agent as described in the 'When to Use' section. 2. Boundary markers: Absent; no specific delimiters are defined to isolate the transcript from instructions. 3. Capability inventory: The skill references the 'masking-royal-news' tool and Google search functionality. 4. Sanitization: Absent; there are no instructions for sanitizing or escaping the content of the transcript before processing.
Audit Metadata