egghead-slack

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill indexes and processes data from Slack channels, DMs, and files, which are sources of untrusted external content.
  • Ingestion points: The skill relies on Slack API endpoints such as conversations.history and search.messages to ingest content.
  • Boundary markers: The skill documentation lacks explicit boundary markers or instructions for the agent to ignore potentially malicious commands embedded in indexed messages.
  • Capability inventory: The skill allows the agent to send messages (chat:postMessage) and upload files using bot and user tokens, which could be exploited if the agent obeys instructions from ingested Slack data.
  • Sanitization: No sanitization or content validation logic is specified for the data entering the intelligence pipeline.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:43 PM