Security Audit
PandaDoc Automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
PandaDoc Automation received a trust score of 85/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Webhook creation allows arbitrary URL for data exfiltration.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Webhook creation allows arbitrary URL for data exfiltration The `PANDADOC_CREATE_WEBHOOK` tool allows the creation of webhooks with an arbitrary `url` parameter. This means an attacker could prompt the agent to create a webhook pointing to a server they control, potentially exfiltrating sensitive PandaDoc event data (e.g., document state changes, recipient completion status) to an external malicious endpoint. Implement strict URL validation (e.g., allowlisting domains) for webhook endpoints if possible, or ensure the LLM is robustly guarded against malicious URL inputs. Users should be warned about the risks of providing untrusted URLs for webhooks. | LLM | SKILL.md:100 |
Scan History
Embed Code
[](https://skillshield.io/report/017a53a1819c0161)
Powered by SkillShield