pexels-media

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads high-quality media content and metadata from Pexels, a well-known and established stock media service. This functionality is the primary purpose of the skill and uses official API endpoints.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data received from the Pexels API, which represents a potential ingestion surface for untrusted content.
  • Ingestion points: The skill ingests data via Bash scripts in SKILL.md that use curl to retrieve JSON responses from the Pexels API.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded content are used when processing the API data.
  • Capability inventory: The skill utilizes Bash (including curl and jq), Write (to create sidecar metadata files), and WebFetch to interact with the external service.
  • Sanitization: The skill employs jq to strictly parse and extract specific fields from the JSON API responses before saving them to disk, which is a standard and secure practice for handling structured data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 03:59 PM