Security Audit
anysiteio/agent-skills:skills/anysite-lead-generation
github.com/anysiteio/agent-skillsTrust Assessment
anysiteio/agent-skills:skills/anysite-lead-generation 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 Web scraping tool allows arbitrary URL access, potential for SSRF.
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 April 1, 2026 (commit 5cefedb0). 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 | Web scraping tool allows arbitrary URL access, potential for SSRF The `webparser` tool, exposed via `mcp__anysite__execute` with `source: "webparser"`, allows the AI agent to specify an arbitrary `url` parameter. If the `anysite` MCP server executing this request is hosted in a network with access to internal resources, a compromised agent (e.g., via prompt injection) could be instructed to perform Server-Side Request Forgery (SSRF) attacks. This could lead to internal network scanning, access to sensitive internal web applications, or information disclosure. Implement strict URL validation and sanitization on the `anysite` MCP server to prevent access to internal IP ranges, loopback addresses, and non-HTTP/HTTPS schemes. Consider whitelisting allowed domains or implementing a proxy that filters requests. The skill documentation could also advise agents to be cautious with user-provided URLs for web scraping. | LLM | SKILL.md:100 |
Scan History
Embed Code
[](https://skillshield.io/report/776db6d0b7462c22)
Powered by SkillShield