test-slack-app
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of Slack CLI commands such as
slack doctor,slack manifest validate, andslack runto perform health checks and start the application. It also provides instructions for running user-controlled start scripts likenpm startorpython app.pyand setting environment variables viaslack env set. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it is designed to read and process external, potentially untrusted data to provide developer guidance.
- Ingestion points: The agent reads the application's source code to identify registered listeners (Step 3a) and monitors runtime logs provided by the developer (Step 3c).
- Boundary markers: None; the skill does not instruct the agent to use specific delimiters or ignore instructions found within the ingested source code or logs.
- Capability inventory: The skill has access to shell command execution (via the Slack CLI and local run commands) and environment variable management.
- Sanitization: None; the skill lacks explicit instructions for escaping or validating the content extracted from the application's source or logs before processing.
Audit Metadata