clone

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local wrapper script api-request.sh to perform multiple API operations against the Spotify Ads platform.
  • [DYNAMIC_EXECUTION]: The skill employs the eval command to load environment variables from the output of its internal API tool. While this is a common pattern for configuration management in CLI tools, it involves the execution of dynamically generated shell strings.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external campaign and ad set data which is then interpolated into prompts to generate new draft entities, creating a potential vector for indirect instructions. 1. Ingestion points: Source campaign, ad set, and ad metadata fetched via GET requests. 2. Boundary markers: Absent in the interpolation process. 3. Capability inventory: Access to bash command execution and API write capabilities (POST). 4. Sanitization: The skill relies on a human-in-the-loop 'Clone Plan' confirmation step to verify changes rather than programmatic sanitization of the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 02:52 AM