Security Audit
Dynamics 365 Automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
Dynamics 365 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 Broad CRM Data Access and Potential User Impersonation.
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 | Broad CRM Data Access and Potential User Impersonation The skill provides extensive capabilities for creating, updating, and retrieving sensitive data across various Dynamics 365 CRM entities (leads, accounts, contacts, opportunities, sales orders, invoices, cases). While this is the intended function of a CRM automation skill, the broad scope means that if the LLM is compromised or misused (e.g., via prompt injection), it could lead to significant unauthorized data manipulation, deletion, or exposure of sensitive customer information.
Additionally, the documentation explicitly notes a 'Known Pitfall' regarding the `user_id` parameter: 'Most tools default `user_id` to "me" for the authenticated user. Override only when acting on behalf of another user.' This indicates that the skill can be instructed to perform actions on behalf of other users. If the authenticated user has the necessary permissions, this capability could be exploited for privilege escalation or impersonation within Dynamics 365, allowing an attacker to perform actions as a different user. Implement strict access controls and least privilege principles within Dynamics 365 for the account used by the skill. Ensure that the LLM's access to this skill is carefully managed and monitored. For the `user_id` override, consider if this functionality is strictly necessary; if not, disable or restrict the ability to specify arbitrary `user_id` values at the platform level. If necessary, ensure robust authorization checks are in place for any `user_id` specified to prevent unauthorized impersonation. | LLM | SKILL.md:150 |
Scan History
Embed Code
[](https://skillshield.io/report/26f23cda8f47e8ae)
Powered by SkillShield