service-de-channel-create
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is authored by the vendor Salesforce (forcedotcom) and facilitates the configuration of official messaging channels within the Salesforce platform using sanctioned CLI tools and APIs.
- [EXTERNAL_DOWNLOADS]: The skill makes a network request to the well-known service provider LINE (api.line.me) to validate access tokens. This is a legitimate functional requirement for messaging integration and targets a well-known service domain.
- [COMMAND_EXECUTION]: The skill utilizes common CLI tools (sf, curl, jq) to perform its tasks. It follows security best practices, such as using mktemp for isolated temporary directories and structured input handling in jq commands.
- [PROMPT_INJECTION]: The internal redirection logic (Stage 0) is a design pattern for modular skills meant to guide agents to the correct orchestrator and does not represent a malicious attempt to bypass safety guidelines or conceal malicious intent.
Audit Metadata