ClawHub
Back to skill

Security audit

Compliance Management

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent external compliance-assessment API integration, but users should treat submitted assessment details as sensitive third-party data.

Install only if you are comfortable sending compliance posture, control evidence, organization metadata, session IDs, and optional user identifiers to the provider’s external API. Avoid submitting secrets, customer data, confidential audit artifacts, or unredacted internal details unless you have reviewed the provider’s privacy, retention, and security terms.

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
  • 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
96% confidence
Finding

The skill solicits and describes submission of detailed organizational compliance data, including control responses, evidence, organization profile, and identifiers, but does not warn users that this information will be sent to a third-party external API. That omission can cause users to unknowingly transmit sensitive security posture and audit evidence outside their environment, increasing confidentiality and regulatory risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The skill is explicitly integrated with an external domain and directs traffic to api.mkkpro.com for compliance-management functions. In this context, the transmitted content may include sensitive compliance evidence, control implementation details, and organizational metadata, so external transmission creates a real data exposure surface even if the endpoint itself is legitimate.

Content

Scanner excerpt · SKILL.md (reported line 195)May include surrounding context.

md
# References

- Kong Route: https://api.mkkpro.com/compliance/management-platform
- API Docs: https://api.mkkpro.com:8103/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This is a manifest/config file, so vague-trigger review applies. The description "Perform comprehensive compliance assessment" is broad and does not define invocation boundaries, exclusions, or narrower conditions for when this operation should be selected, which can contribute to unintended activation in tool-selection contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The phrase "Get list of all supported frameworks" is generic in a manifest-style API description and does not indicate when this operation should or should not be invoked. Without scope constraints or disambiguating examples, it may overlap with broader user requests about compliance guidance.

Content

No source excerpt is available for this finding.