sponsor-finder

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to instructions embedded in third-party data retrieved during its execution. * Ingestion points: The skill retrieves and reads untrusted data from YouTube video descriptions and transcripts using the get_channel, get_video, and get_video_transcript tools. * Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' directives to isolate external content from the agent's core instructions. * Capability inventory: The skill uses read-only tools for searching and metadata retrieval (e.g., search_related_channels, get_video); it does not have access to file-writing, system commands, or external network requests outside the MCP scope. * Sanitization: There is no evidence of text sanitization or filtering logic to prevent the agent from following instructions potentially hidden in the ingested transcripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 04:32 PM