test-slack-app
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the Slack CLI to execute environmental health checks and validation commands including
slack doctor,slack auth list, andslack manifest validate. These are standard tools provided by the vendor for developers to verify their setup. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes local application source code to identify registered interaction listeners. Ingestion point: Application source code files read in Step 3a. Boundary markers: None. Capability inventory: The skill can execute shell commands via the Slack CLI (Step 1c). Sanitization: The risk is mitigated by the instruction for the developer to manually confirm the app's behavior in the Slack UI rather than the agent acting autonomously on the code content.
- [EXTERNAL_DOWNLOADS]: The skill references official documentation at
docs.slack.devto guide developers in setting up sandboxes. This is a trusted, well-known service from the vendor.
Audit Metadata