sinch-functions
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill references the installation of vendor-owned CLI tools and runtime libraries (
@sinch/cli,@sinch/functions-runtime,Sinch.Functions.Runtime) from official package registries. These are necessary components for the serverless platform and are provided by the verified author. - [DATA_EXFILTRATION]: No unauthorized exfiltration patterns were detected. The skill promotes secure credential handling by instructing users to use the platform's native secret management system and the OS keychain instead of hardcoding sensitive information in source code or configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill correctly identifies that external data from voice and messaging webhooks is untrusted. It provides explicit security guidance to validate these inputs and warns against interpolating them into prompts or shell commands, which mitigates the risk of indirect injection attacks.
- [COMMAND_EXECUTION]: Terminal commands mentioned (e.g.,
sinch functions deploy,sinch secrets add) are standard administrative operations for the platform and do not involve unsafe user input injection.
Audit Metadata