Back to skill

Security audit

Rankizz Local Site Audit

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because its crawler has a reported risk of sending requests to internal network services, while scanner coverage was partial.

Consider the internal-network request risk before installing, especially if you would run the crawler where it can reach private services. The skill’s tool scope is undeclared, and the host runtime’s permissions are unknown. Skillspector’s analysis was partial because it could not resolve a path-like reference, so the evidence is incomplete.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/crawl_site.py
Finding

Separate DNS validation and connection allow private-network SSRF

Content
View full analysis

Impact

The attacker can induce HTTP GET requests to reachable internal services, including attacker-selected paths and ports. This can contact otherwise inaccessible endpoints and trigger effects on services with state-changing GET handlers. Arbitrary response exfiltration or credential theft is not established by this code.

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
## Establish scope

Use an explicit Quick or Full request without asking again. Otherwise ask the user to choose:

- **Quick:** homepage, robots, sitemap, and up to 10 representative pages.
- **Full:** a user-approved, bounded crawl budget and optional path scope.