Security Audit
msg91-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
msg91-automation 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 Excessive Permissions via Broad Tool Access.
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 17, 2026 (commit 99e2a295). 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 | Excessive Permissions via Broad Tool Access The skill, named 'msg91-automation' and described as automating Msg91 tasks, explicitly instructs the agent to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The function `run_composio_tool()` implies the ability to execute any tool available within the broader Composio ecosystem, not just those specific to Msg91. This grants significantly broader permissions than what is suggested by the skill's name and description, potentially allowing the agent to access and operate other, more sensitive toolkits if they are available through the Rube MCP. If the skill is intended to be limited to Msg91 operations, remove the instruction to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` or clarify that its usage is strictly confined to Msg91-specific tools. If the skill is indeed intended to have broader Composio tool access, update the skill's name and description to accurately reflect its wider capabilities and potential scope. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/96e65407c5ab78ae)
Powered by SkillShield