appdeploy
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
curlfor registration and managing app deployments through a remote API. - [DATA_EXFILTRATION]: Local project code is transmitted to the
api-v2.appdeploy.aiendpoint as part of the intended deployment workflow. - [INDIRECT_PROMPT_INJECTION]: The tool
get_deploy_instructionsfetches instructions from an external API that the agent is directed to obey, representing an indirect injection surface. * Ingestion points: Instruction text retrieved from the remote API inSKILL.md. * Boundary markers: None identified. * Capability inventory: Ability to send local files, read remote files, and delete resources. * Sanitization: No specific sanitization or integrity checking of the remote instructions is documented.
Audit Metadata