slack-user-context
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Slack to guide agent decision-making and response generation.
- Ingestion points: Uses
im:historyto read direct message context andsearch:read.publicto retrieve content from public channels (SKILL.md). - Boundary markers: The instructions lack specific boundary markers or safety directives to prevent the agent from following instructions embedded within the retrieved Slack messages.
- Capability inventory: The skill influences escalation routing and integrates with
pyATSskills and incident workflows, which typically involve executing commands on network infrastructure (SKILL.md). - Sanitization: No sanitization or filtering logic is defined for the external message content before it is used to determine response depth or escalation paths.
Audit Metadata