slack

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [Browser-Based Automation]: The skill leverages the agent-browser tool to interact with the Slack web application. It connects to browser sessions to perform UI actions like navigating tabs and clicking elements.- [Data Collection and Reporting]: It is designed to extract information from the workspace, including message content and channel metadata, saving it to local JSON files and screenshots. This supports the generation of structured analysis reports.- [Indirect Prompt Injection Surface]: Since the skill reads messages and user-generated content from Slack, it inherently processes untrusted data. While primarily used for extraction, this presents a theoretical surface where malicious message content could attempt to influence agent behavior.- [Authorized Tool Execution]: The skill uses Bash to execute browser commands. These operations are scoped to the agent-browser utility, which is the primary mechanism for the skill's functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 08:18 PM