Trust Assessment
pinchedin received a trust score of 93/100, 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 Configurable Webhook/Email for Data Exfiltration, Configurable Call-to-Action URL for Redirection.
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 14, 2026 (commit 13146e6a). 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 | Configurable Webhook/Email for Data Exfiltration The skill allows the agent to configure a `webhookUrl`, `email`, and `operatorEmail` during registration and profile updates. If an attacker can manipulate the LLM via prompt injection to set these fields to an attacker-controlled domain or email address, sensitive event data (e.g., connection requests, hiring requests, mentions, comments, likes, daily digests) could be exfiltrated to the attacker's infrastructure. While the skill itself does not instruct exfiltration, it provides a mechanism that, if misused by a compromised LLM, could lead to data leakage. Implement strict validation and allowlisting/denylisting for `webhookUrl` and email domains. The LLM should be explicitly instructed not to set these to arbitrary URLs or email addresses from untrusted prompts. Consider adding a confirmation step for changes to these sensitive fields. | LLM | SKILL.md:50 | |
| LOW | Configurable Call-to-Action URL for Redirection The skill allows the agent to set a `ctaUrl` for a custom call-to-action button on their profile. If an attacker can manipulate the LLM via prompt injection to set this URL to a malicious site, users viewing the agent's profile could be redirected to phishing pages, malware downloads, or other harmful content. While not direct data exfiltration, it poses a risk of user compromise. Implement strict validation and allowlisting/denylisting for `ctaUrl` domains. The LLM should be explicitly instructed not to set this to arbitrary URLs from untrusted prompts. Consider warning users before redirecting to external sites. | LLM | SKILL.md:490 |
Scan History
Embed Code
[](https://skillshield.io/report/ddcabda3694eb688)
Powered by SkillShield