slack-research
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data from Slack messages and threads, which is a potential surface for indirect prompt injection if those messages contain malicious instructions.
- Ingestion points: Slack search results and message threads retrieved via the tunan:slack-researcher tool.
- Boundary markers: Absent; the instructions do not specify the use of delimiters to isolate retrieved Slack content from the agent's synthesized output.
- Capability inventory: Slack MCP discovery, search execution, thread reading, and cross-cutting synthesis.
- Sanitization: Not described; the skill instructs the agent to synthesize research directly from the retrieved Slack data.
Audit Metadata