skills/craftos-dev/craftbot/slack/Gen Agent Trust Hub

slack

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its ability to ingest and process data from external Slack channels.
  • Ingestion points: External Slack message content is retrieved via the readMessages action defined in SKILL.md.
  • Boundary markers: The instructions lack explicit boundary markers or 'ignore' instructions to isolate message content from agent logic.
  • Capability inventory: The skill possesses significant capabilities, including sendMessage, editMessage, deleteMessage, and pinMessage, which could be manipulated by malicious message content.
  • Sanitization: There is no evidence of sanitization or validation of the text retrieved from Slack channels before it enters the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 05:35 PM
Security Audit — agent-trust-hub — slack