ClawHub
Back to skill

Security audit

ClawHub Publisher Stats

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent public ClawHub statistics fetcher, with limited caution needed for live network requests and Markdown report rendering.

Install only if you are comfortable with the skill making live requests to public ClawHub-related sites. Prefer JSON output for automated reuse, and avoid passing unusually large --limit or --workers values.

A.I.G

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/fetch_clawhub_publisher_stats.py:218
Finding

Unescaped Remote Metadata in Markdown Output

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/fetch_clawhub_publisher_stats.py:120
Finding

Unbounded Request and Worker Parameters Permit Resource Exhaustion

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
3. Use `--format json` when the user wants machine-readable output.

## Output Rules

- Always report the author aggregate block first when available:
  - rank

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs the agent to run a bundled Python script that fetches live data from public pages, which implies network access, but the manifest does not declare any tool scope or allowed-tools restrictions. This creates a least-privilege and governance gap: an agent may execute network-capable code without explicit authorization boundaries, making misuse or unexpected external access harder to audit and control.

Content

No source excerpt is available for this finding.