Back to skill

Security audit

Cisco ASA Hardening

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Cisco ASA configuration generator that calls an external API, with privacy notes around session and user identifiers but no evidence of hidden execution or malicious behavior.

Install only if you are comfortable sending hardening options and session metadata to the listed external provider. Avoid including real user identifiers, live infrastructure secrets, internal IPs, or production-only details unless you have reviewed the provider's privacy and retention practices.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill’s example request includes sessionId, userId, and timestamp fields, but the documentation does not clearly warn users that these identifiers may be sent to an external third-party API. This creates a privacy and data-governance risk because operators may unknowingly transmit user/session metadata to an external service while using a security-sensitive hardening tool.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The skill references an external API endpoint hosted on api.mkkpro.com, indicating that user-supplied data and generated configuration requests are likely transmitted outside the local trust boundary. In the context of a firewall-hardening tool, those requests can reveal sensitive infrastructure details, operational timing, and administrative metadata to a third party if not clearly disclosed and properly governed.

Content

Scanner excerpt · SKILL.md (reported line 146)May include surrounding context.

md
## References

- Kong Route: https://api.mkkpro.com/hardening/cisco-asa
- API Docs: https://api.mkkpro.com:8142/docs

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This is a manifest/config file, so vague-trigger review applies. The summary "Generate" is extremely generic and overlaps with common language, providing no clear scope for when this skill/API should be invoked versus other generation tasks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The request schema collects sessionId and optional userId alongside hardening input, but the API specification provides no user-facing notice, purpose limitation, or minimization guidance for transmitting these identifiers. In an agent-skill context, this can lead to unnecessary disclosure of session-linked or user-linked metadata to a third-party service, increasing privacy risk and enabling correlation, tracking, or accidental retention of identifiers unrelated to firewall hardening.

Content

No source excerpt is available for this finding.