ce-slack-research
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from Slack messages which could contain malicious instructions designed to influence the agent's synthesis.\n
- Ingestion points: Slack search results and thread content retrieved via the Slack MCP integration (SKILL.md).\n
- Boundary markers: No specific boundary markers or 'ignore' instructions are provided to separate Slack content from the agent's task instructions.\n
- Capability inventory: The skill dispatches a synthesis task to a sub-agent; however, it lacks dangerous capabilities such as file system writes or unauthorized network requests in the documented workflow.\n
- Sanitization: There is no evidence of sanitization or filtering applied to the Slack data before processing.
Audit Metadata