skills/xyaz1313/xyskill/xy-clip/Gen Agent Trust Hub

xy-clip

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided text (transcripts) to generate video scripts.
  • Ingestion points: SKILL.md indicates the skill accepts long transcripts from users for analysis and slicing.
  • Boundary markers: The instructions do not explicitly define boundary markers for the input data to prevent the model from following instructions embedded within the transcript, although it does enforce a "zero-addition" policy for output.
  • Capability inventory: The skill is limited to text generation and markdown output based on the provided input; no network operations, file writing, or command execution capabilities are present in the provided files.
  • Sanitization: There are no explicit instructions to sanitize or escape the input content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:59 AM
Security Audit — agent-trust-hub — xy-clip