ClawHub
Back to skill

Security audit

Slack Actions

Security checks for vulnerabilities and agentic risk

Overview

This Slack automation skill is transparent about using a bot token to read and change Slack content, and I found no hidden code or deceptive behavior.

Install with a dedicated Slack bot token, grant only the listed scopes and channels needed, and confirm channel IDs, message IDs, and message text before any send, edit, pin, unpin, or delete action. Do not use a personal user token or broad workspace permissions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation guidance says to activate when the user requests Slack actions, but it does not define hard boundaries for intent detection, trusted context, or when not to invoke the skill. Because this skill has authenticated write and read capabilities in Slack, ambiguous routing increases the risk of prompt-to-action confusion and accidental execution of privileged operations from conversational text.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger examples are broad natural-language phrases like “Send this to #engineering” and “Pin that message,” which can plausibly appear in ordinary conversation or quoted text. In an agentic system, this ambiguity can cause unintended activation of a privileged Slack-writing skill, leading to unauthorized message posting, reactions, pinning, or deletion if paired with weak confirmation logic.

Content

No source excerpt is available for this finding.

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SKILL.md (reported line 367)May include surrounding context.

md
* Modify workspace settings
* Manage billing
* Bypass permissions
* Escalate privileges

All operations respect Slack API constraints.

Static analysis

No suspicious patterns detected.