assets

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to perform file operations such as checking file size (stat), splitting files for chunked uploads (split), and removing temporary files (rm). It also uses curl to interact with the Spotify Ads API.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface where untrusted data is interpolated into shell commands.
  • Ingestion points: The skill ingests user-supplied file paths from the command line and data from Spotify API JSON responses, such as asset IDs and upload session IDs.
  • Boundary markers: There are no explicit boundary markers or instructions to treat data as untrusted.
  • Capability inventory: The skill has access to the Bash tool for network operations and file system management, and the Read tool for accessing local files.
  • Sanitization: No explicit sanitization or escaping instructions are provided for the user-supplied paths or API-derived variables before they are used in shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 02:52 AM