monitor
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
Bashtool to execute a local scriptapi-request.shfor interacting with the Spotify Ads API and performing health diagnostics. - [DYNAMIC_EXECUTION]: The skill employs
eval $(api --env)in theSKILL.mdfile to dynamically assign environment variables (such asTOKENandAD_ACCOUNT_ID) based on the output of a local execution wrapper. While this is a common pattern for CLI tools to export configuration, it represents runtime code assembly. - [INDIRECT_PROMPT_INJECTION]: The skill fetches external data, including campaign and ad set names, from the Spotify Ads API and renders them directly into markdown tables for the user.
- Ingestion points: API responses from
ad_accounts/{ad_account_id}/campaignsandad_setsendpoints referenced inSKILL.md. - Boundary markers: Data is delimited within markdown table structures.
- Capability inventory: The skill has access to the
Bashtool for further API interactions and theReadtool for accessing local files. - Sanitization: No explicit sanitization or escaping of campaign-controlled strings is defined in the prompt instructions before rendering to the agent's context.
Audit Metadata