youtube-search

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from YouTube search results, including video titles and metadata. This provides a potential surface for indirect prompt injection if an attacker-controlled video appears in search results. However, the skill explicitly instructs the agent to treat retrieved text as source material rather than instructions.
  • Ingestion points: SKILL.md (YouTube search result fields like title, channel, etc.)
  • Boundary markers: Present (instruction to treat retrieved text as source material)
  • Capability inventory: Data retrieval and processing; the provided example script prints output via json.dumps but does not execute it.
  • Sanitization: None explicitly mentioned for the ingestion of metadata strings.
  • [EXTERNAL_DOWNLOADS]: The documentation guides the user to install the mcp and httpx Python packages via pip. These are standard, well-known libraries required for the skill's functionality.
  • [DATA_EXFILTRATION]: The skill communicates with data.flashdata.dev to perform searches. This domain belongs to the skill's vendor and is the intended destination for API requests. The skill correctly recommends managing the API key through environment variables or secret managers.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 07:37 AM