trend-to-song

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a process for ingesting untrusted data from social media and viral trends to create content, which introduces a surface for indirect prompt injection.
  • Ingestion points: Viral TikTok content, reality TV discourse, and meme metadata (SKILL.md).
  • Boundary markers: No delimiters or instructions are provided to the agent to ignore potentially malicious embedded content in the ingested trends.
  • Capability inventory: The skill facilitates the creation of song briefs and coordinates with external agents for media production.
  • Sanitization: There are no documented steps for validating or sanitizing the trend data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 03:04 AM