wk-team-hud
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a bash script snippet to validate that required environment variables (
WK_SKILLS_TEAM_SLACK_HANDLE,WK_SKILLS_TEAM_JIRA,WK_SKILLS_TEAM_GITHUB) are set. This is a standard and safe parameter validation technique. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill uses environment variables for configuration and explicitly instructs the user to store a local cache at
$WK_SKILLS_HOME/config/team-hud.yaml. It correctly advises that this file should be gitignored to prevent accidental exposure of mapping data. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from various external APIs (Slack messages, Jira tickets, GitHub PRs). While this presents an attack surface for indirect prompt injection, the skill's purpose is to summarize this data for a dashboard, and it lacks dangerous capabilities like autonomous code execution or sensitive file writes based on that data. The severity is low as it follows standard data aggregation patterns.
- [AUTONOMY_AND_CONCEALMENT]: The skill implements a 'Hard Rule' requiring explicit user confirmation via
AskUserQuestionbefore caching channel mappings, preventing silent misconfiguration or 'cache poisoning'.
Audit Metadata