dashboard

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 the Bash tool to execute a local script located at scripts/api-request.sh. This script functions as the primary interface for making authenticated requests to the Spotify Ads API.
  • [DYNAMIC_EXECUTION]: The instructions recommend using eval on the output of the local api --env command. This pattern is used to dynamically set environment variables such as TOKEN and AD_ACCOUNT_ID within the agent's execution environment from the skill's own configuration script.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and display campaign metadata (names, status) and metrics from the Spotify Ads API, which constitutes an external data surface.
  • Ingestion points: Data enters the context via api GET requests to the ad_accounts endpoints defined in SKILL.md.
  • Boundary markers: There are no specific delimiters or instruction-ignore warnings defined for the display of campaign names or targeting descriptions which might contain untrusted content.
  • Capability inventory: The skill possesses Bash execution capabilities used to run the api-request.sh wrapper and calculate pacing metrics.
  • Sanitization: The instructions do not specify sanitization or escaping steps for the raw text returned by the API before it is rendered into the dashboard table.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 02:52 AM