ClawHub
Back to skill

Security audit

SABSA Architecture

Security checks for vulnerabilities and agentic risk

Overview

The skill appears aligned with its stated assessment purpose, but it asks users to send sensitive security architecture details to an external service without enough privacy or handling disclosure.

Install only if you are comfortable sending the assessment inputs to the provider's external service. Before using it with real enterprise data, redact secrets and unnecessary identifiers, avoid regulated or highly confidential details unless approved, and confirm the provider's retention, logging, access control, and contractual privacy 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
92% confidence
Finding

The skill explicitly solicits detailed organizational security architecture data, including asset classifications, roles, locations, motivations, and process maturity, but provides no privacy, confidentiality, or data-handling warning. In a security-assessment context, this materially increases the risk that users submit sensitive internal information to a third-party service without understanding retention, sharing, or jurisdictional implications.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The skill directs users to an external API endpoint for processing, which implies transmission of potentially sensitive enterprise security architecture data outside the local trust boundary. Given the nature of the collected data, external transmission is security-relevant even if expected behavior, because compromise, misconfiguration, or undisclosed retention at the remote service could expose high-value internal security information.

Content

Scanner excerpt · SKILL.md (reported line 235)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/compliance/sabsa-architecture
- **API Docs:** https://api.mkkpro.com:8102/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This is a JSON manifest-style file, so vague-trigger review applies. The API operation is described only as "Generate Assessment" / "Generate comprehensive SABSA security architecture assessment" without any narrowing context, activation constraints, or exclusions, which leaves invocation scope underspecified for a skill manifest-like interface.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

The only policy category in scope is natural-language language/locale violations, and none are clearly present here. However, because this field is named userId and presented in a user-facing schema without explanatory language, it may imply organizational handling expectations without any documented user choice or justification; this is weak evidence and only a low-confidence concern.

Content

No source excerpt is available for this finding.