Security Audit
Attio Automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
Attio Automation received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned dependency in manifest, Skill provides broad access to sensitive CRM data.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill provides broad access to sensitive CRM data The skill exposes tools that allow for extensive and potentially unconstrained retrieval of sensitive CRM data across the entire workspace. Specifically, the `ATTIO_SEARCH_RECORDS` tool, when used with `request_as: {"type": "workspace"}`, enables a 'full workspace search'. Additionally, `ATTIO_QUERY_RECORDS` and `ATTIO_LIST_RECORDS` can retrieve large volumes of data. While this is intended functionality for a CRM automation tool, an LLM, if compromised by a malicious prompt, could be instructed to exfiltrate large volumes of sensitive customer data without granular restrictions. Implement granular access controls or rate limits within the skill's integration layer to restrict the volume or scope of data an LLM can retrieve, even if the underlying Attio account has broad permissions. Consider adding explicit user confirmation steps for broad data export operations. | LLM | SKILL.md:40 | |
| MEDIUM | Unpinned dependency in manifest The skill manifest specifies a dependency `rube` without a version constraint. This allows for automatic updates to potentially incompatible or malicious versions, introducing supply chain risks if a compromised version of `rube` is published. Pin the dependency `rube` to a specific version or version range (e.g., `"rube": ["rube==1.2.3"]` or `"rube": ["rube>=1.0.0,<2.0.0"]`) to ensure stability and security. | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/5e04ef52bc4b9db4)
Powered by SkillShield