ads-manager
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
adaptyCLI to perform actions like creating campaigns, updating bids, and pausing keywords. - [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the
adaptyCLI tool from the global NPM registry. - [REMOTE_CODE_EXECUTION]: The skill executes the Adapty CLI directly from the network using the
npxcommand. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external data that may contain malicious instructions.
- Ingestion points: Data is ingested via
asa search-terms listandasa competitors summaryas described inSKILL.mdandreferences/asa-metrics.md. - Boundary markers: No delimiters or warnings are provided to the agent regarding the potential for instructions embedded in external data.
- Capability inventory: The skill allows the agent to execute commands that modify real-world marketing spend and configurations.
- Sanitization: The instructions do not include any logic to sanitize or filter the data fetched from external sources.
Audit Metadata