ClawHub
Back to skill

Security audit

Cisco Firewall Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Cisco firewall audit skill whose commands are disclosed and aligned with read-only security review work.

Install only if you are authorized to audit the Cisco firewalls involved. Use read-only ASA/FMC accounts where possible, avoid entering configuration mode, and treat collected configs, VPN details, tokens, and logs as sensitive network security data.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 333)May include surrounding context.

md
| Finding | Severity | Rationale |
|---------|----------|-----------|
| **[ASA]** `permit ip any any` in interface ACL | Critical | Permits all IP traffic — no access restriction |
| **[FTD]** ACP default action set to Allow | Critical | All unmatched traffic permitted without inspection |
| **[FTD]** Prefilter Trust rule with broad match (any/any) | Critical | Traffic bypasses all Snort inspection |
| **[ASA]** No global service-policy applied | High | No application-layer inspection on any traffic |

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The documentation explicitly refers readers to a dual-platform read-only command reference, but later instructs use of packet-tracer for policy verification. Even if packet-tracer is non-persistent, this contradicts the earlier framing that the command set is purely read-only.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The manifest presents the skill as a read-only firewall audit, but the documented procedure includes changeto context <name> and later packet-tracer usage for verification. While these may be operationally common in audits, they go beyond passive viewing and are not clearly framed as exceptions to the read-only description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.