Security Audit
proxiedmail-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
proxiedmail-automation received a trust score of 85/100, 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 grants broad, dynamic tool execution 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 20, 2026 (commit 27904475). 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 grants broad, dynamic tool execution capabilities The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` with dynamically discovered tool slugs from the `proxiedmail` toolkit. This allows the LLM to execute any operation exposed by the `proxiedmail` toolkit without explicit constraints defined within the skill itself. Depending on the `proxiedmail` toolkit's capabilities, this could lead to sensitive actions (e.g., sending emails, managing contacts, accessing private data) being performed by the LLM if not properly sandboxed or approved by a human. Implement stricter access controls or human-in-the-loop approval for sensitive `proxiedmail` operations. Consider defining a more granular set of allowed tool slugs or arguments within the skill's instructions, rather than allowing arbitrary execution of discovered tools. Alternatively, ensure the underlying `proxiedmail` toolkit has fine-grained permissions that can be configured by the user. | LLM | SKILL.md:50 |
Scan History
Embed Code
[](https://skillshield.io/report/3310b4700c348025)
Powered by SkillShield