Security Audit
findymail-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
findymail-automation received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Dynamic Tool Discovery and Execution Grants Broad 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 | |
|---|---|---|---|---|
| MEDIUM | Dynamic Tool Discovery and Execution Grants Broad Access The skill instructs the LLM to dynamically discover and execute tools provided by the Composio Rube MCP for Findymail. It encourages the use of `RUBE_SEARCH_TOOLS` to find available tools and `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` to execute them. This pattern grants the LLM the ability to perform any action exposed by the Findymail toolkit within Composio, which could include sensitive operations like data modification, deletion, or broad data export, without explicit constraints defined within the skill itself. The actual scope of permissions depends on the underlying Composio toolkit, but the skill enables the LLM to access the full breadth of those capabilities, potentially leading to unintended or unauthorized actions if the LLM is not properly constrained. If possible, restrict the `use_case` in `RUBE_SEARCH_TOOLS` to a more narrow set of operations, or explicitly list allowed `tool_slug`s if the LLM should only perform specific actions. Avoid instructing the LLM to use generic execution tools like `RUBE_REMOTE_WORKBENCH` for `run_composio_tool()` unless absolutely necessary and with strict guardrails. Implement external authorization checks on the Composio platform to ensure the agent's actions are within acceptable bounds. | LLM | SKILL.md:34 |
Scan History
Embed Code
[](https://skillshield.io/report/16639abd5db09907)
Powered by SkillShield