Trust Assessment
slacks received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill describes broad Slack access capabilities.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill describes broad Slack access capabilities The `slacks` skill describes a tool that provides extensive access to Slack, including reading messages, sending/editing/deleting messages, managing pins, and fetching member information. All action groups (reactions, messages, pins, memberInfo, emojiList) are listed as 'enabled' by default. This broad scope, particularly the ability to read and modify messages and access user data, presents a significant attack surface. If an attacker can manipulate the LLM to use this tool, they could potentially exfiltrate sensitive information from channels, impersonate the bot, or tamper with communications. Review the necessity of all listed Slack permissions for the bot's intended function. Implement granular access control for the underlying Slack bot token, adhering to the principle of least privilege. If possible, break down the skill into smaller, more focused skills with limited capabilities. Ensure the LLM's access to this tool is carefully controlled and monitored. | LLM | SKILL.md:24 |
Scan History
Embed Code
[](https://skillshield.io/report/e8e7d7f2e10c2db3)
Powered by SkillShield