campaigns
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute a local utility script,api-request.sh, which facilitates communication with the Spotify Ads API. - [DYNAMIC_EXECUTION]: The instruction
eval $(api --env)is used to load necessary environment variables (such as tokens and account IDs) into the shell context by executing the output generated by theapiscript. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from the Spotify Ads API, including campaign details and product catalogs, which represents an attack surface for indirect instructions.
- Ingestion points: The skill fetches campaign data, draft statuses, and validation catalogs through
GETrequests to the Spotify Ads API. - Boundary markers: No explicit delimiters or warnings are used to separate API-returned data from the agent's internal instructions.
- Capability inventory: The skill has access to
Bash(via the wrapper script),Read(to access reference files), andAskUserQuestion(to prompt for configuration). - Sanitization: There is no explicit sanitization logic mentioned for the API response content before it is displayed or processed.
Audit Metadata