slack

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting untrusted data from external sources.
  • Ingestion points: The readMessages action in SKILL.md allows the agent to fetch content from Slack channels and DMs.
  • Boundary markers: There are no specified delimiters or instructions to the agent to treat Slack message content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill provides powerful capabilities including sendMessage, editMessage, deleteMessage, pinMessage, and memberInfo which could be exploited if the agent follows instructions hidden within a Slack message.
  • Sanitization: No sanitization, escaping, or validation logic is defined for the content retrieved from Slack.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:44 PM
Security Audit — agent-trust-hub — slack