orbitant-yt-description
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a template for text generation and SEO optimization. It does not utilize any restricted tools or perform system operations.
- [DATA_EXFILTRATION]: Analysis confirmed the absence of credential harvesting, sensitive file access, or unauthorized network communication.
- [PROMPT_INJECTION]: The instructions define a specific task and format for the agent without attempting to override safety protocols or extract system prompts.
- [PROMPT_INJECTION]: The skill processes untrusted transcripts, creating a surface for indirect prompt injection. (1) Ingestion points: Transcripts provided in .vtt or plain text format. (2) Boundary markers: Absent; no delimiters specified in the instructions for input handling. (3) Capability inventory: None; the skill's only output is plain text for user review. (4) Sanitization: Absent; the skill relies on the LLM's inherent processing and human review before publication.
Audit Metadata