skills/heldinhow/openclaw-swarm/slack/Gen Agent Trust Hub

slack

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it reads external data from Slack channels.
  • Ingestion points: The readMessages action (SKILL.md) allows untrusted data to enter the agent's context.
  • Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following commands embedded in Slack messages.
  • Capability inventory: The skill is limited to Slack-specific actions like sendMessage, editMessage, and pinMessage; it lacks access to the file system, shell, or external network beyond Slack.
  • Sanitization: No sanitization or content filtering is described for the retrieved Slack messages.
  • [NO_CODE]: The provided skill content consists of a markdown definition and does not include executable scripts or external package dependencies for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 12:56 PM