slack-workspace-cleanup

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from the Slack web interface, which creates a surface for indirect prompt injection. If an attacker controls content in the user's Slack workspace (such as names or displayed titles), they could potentially influence the agent's behavior. \n- Ingestion points: Workspace inventory data is read from the Slack DOM via snapshots in SKILL.md. \n- Boundary markers: The skill includes a 'Safety boundary' section that explicitly prohibits clicking deactivation buttons and requires inventory review. \n- Capability inventory: The skill uses Chrome DevTools tools to interact with the browser and manage tabs. \n- Sanitization: No explicit sanitization or filtering of the ingested DOM content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 01:34 PM
Security Audit — agent-trust-hub — slack-workspace-cleanup