Security Audit
memberstack-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
memberstack-automation received a trust score of 92/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Broad Tool Execution Capability, Unpinned Rube MCP Dependency.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Broad Tool Execution Capability The skill exposes `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which allow the LLM agent to execute any available Memberstack tool or Composio tool respectively. This grants broad access to Memberstack operations, potentially including sensitive or destructive actions, if the underlying tools permit them. While this is the intended functionality for a general automation skill, it means the agent's effective permissions are very wide, increasing the risk of unintended actions if the agent is compromised or misdirected. Consider implementing finer-grained access control or a whitelist of allowed Memberstack operations if the skill is intended for more restricted use cases. Alternatively, ensure robust guardrails are in place at the agent or platform level to prevent misuse of these broad capabilities. | LLM | SKILL.md:59 | |
| LOW | Unpinned Rube MCP Dependency The skill's manifest specifies a dependency on `rube` within the `mcp` ecosystem but does not pin a specific version. This means the skill will always use the latest available version of Rube MCP, which could introduce unexpected behavior, breaking changes, or new vulnerabilities if not carefully managed by the MCP provider. Pin the `rube` dependency to a specific, known-good version in the skill's manifest to ensure stability and prevent unexpected changes from upstream updates. Example: `{"mcp": ["rube@1.2.3"]}`. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/df3e83f2e6c80516)
Powered by SkillShield