Security Audit
extracta-ai-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
extracta-ai-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 via RUBE_REMOTE_WORKBENCH, 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 via RUBE_REMOTE_WORKBENCH The skill is named `extracta-ai-automation`, implying a specific scope for Extracta AI operations. However, the documentation explicitly mentions and provides an approach for `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. This is a generic mechanism for executing any Composio tool, which could allow the agent to execute tools beyond the intended 'Extracta AI' scope if the underlying Rube MCP does not enforce strict access control based on the skill's manifest or context. This grants broader permissions than the skill's name suggests, potentially increasing the attack surface. If the skill is intended only for Extracta AI operations, ensure that the Rube MCP strictly limits `RUBE_REMOTE_WORKBENCH` and `RUBE_MULTI_EXECUTE_TOOL` to only Extracta AI-related tools when invoked through this skill. Alternatively, rename the skill to reflect its broader Composio automation capabilities if it is indeed designed to interact with multiple Composio toolkits. | LLM | SKILL.md:68 | |
| LOW | Unpinned Rube MCP dependency The skill's manifest declares a dependency on the `rube` MCP (`"mcp": ["rube"]`) without specifying a version or version range. This means that any future version of the Rube MCP could be used, potentially introducing breaking changes, vulnerabilities, or altered behavior without explicit review or testing by the skill developer. This is a standard supply chain risk associated with unpinned dependencies. Pin the Rube MCP dependency to a specific version or version range in the manifest to ensure predictable behavior and mitigate risks from unreviewed updates. For example: `"mcp": ["rube@^1.0.0"]` or `"mcp": ["rube@1.2.3"]`. | LLM | manifest.json:1 |
Scan History
Embed Code
[](https://skillshield.io/report/7c9b288f140d1de1)
Powered by SkillShield