Security Audit
Capsule CRM Automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
Capsule CRM Automation received a trust score of 86/100, 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 Agent has capability to delete CRM contacts.
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 | Agent has capability to delete CRM contacts The skill explicitly grants the agent access to the `CAPSULE_CRM_DELETE_PARTY` tool. This tool allows for the permanent and irreversible deletion of contact records (parties) within Capsule CRM. If the agent's instructions are compromised, for example, through a sophisticated prompt injection attack, an attacker could instruct the agent to delete critical business data, leading to significant and potentially irrecoverable data loss. Implement a human-in-the-loop confirmation step for all destructive operations, especially `DELETE_PARTY`. Alternatively, consider restricting the agent's access to delete functionalities unless absolutely necessary and with strong, explicit user consent. Ensure robust prompt injection defenses are in place to prevent unauthorized execution of such high-impact actions. | LLM | SKILL.md:170 |
Scan History
Embed Code
[](https://skillshield.io/report/d4dfadeb2c87f219)
Powered by SkillShield