Security Audit
fixer-io-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
fixer-io-automation received a trust score of 88/100, 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 enables execution of arbitrary Rube MCP tools.
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 | Skill enables execution of arbitrary Rube MCP tools The skill's 'Core Workflow Pattern' instructs the LLM to first use `RUBE_SEARCH_TOOLS` to discover available tools and then `RUBE_MULTI_EXECUTE_TOOL` to execute any tool identified by its `tool_slug`. While `RUBE_SEARCH_TOOLS` can be guided by a `use_case` parameter (e.g., 'Fixer IO operations'), the `RUBE_MULTI_EXECUTE_TOOL` itself does not enforce this scope. A malicious prompt could instruct the LLM to search for and execute tools unrelated to Fixer IO (e.g., filesystem operations, network access, or other sensitive tools available via Rube MCP), potentially leading to arbitrary command execution, data exfiltration, or unauthorized data manipulation if the Rube MCP has access to such tools. This grants overly broad tool access to the LLM when using this skill, as it allows for dynamic execution of any tool discoverable through Rube MCP. To mitigate this, restrict the `RUBE_MULTI_EXECUTE_TOOL` calls within this skill to a predefined whitelist of `tool_slug`s that are strictly specific to Fixer IO operations. Alternatively, ensure that the `RUBE_SEARCH_TOOLS` implementation is strictly scoped and cannot return non-Fixer IO related tools when invoked within the context of this skill. Implement robust input validation and sanitization on `tool_slug` and `arguments` before execution to prevent malicious payloads. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/3acc412de39571d0)
Powered by SkillShield