ClawHub
Back to skill

Security audit

Afrexai Soc2 Evidence Collector.Skip

Security checks for vulnerabilities and agentic risk

Overview

This SOC2 evidence skill is purpose-aligned and transparent, but users should treat the generated audit collection scripts as sensitive administrative tooling.

Install only if you intend to use an agent for SOC2 evidence preparation. Before running any generated scripts, use authorized least-privilege AWS/GitHub/IdP credentials, scope collection to the audit boundary, store the evidence directory securely, and redact sensitive values before sharing with auditors or third parties.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README promotes automated evidence collection from AWS, GitHub, and identity providers without warning that these scripts may require broad read access to highly sensitive security, identity, and compliance data. In a compliance context, users may trust and run generated scripts against production systems, increasing the chance of over-collection, credential misuse, or unintended transmission of audit artifacts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill includes ready-to-run AWS and GitHub evidence collection scripts that enumerate IAM, MFA, security groups, CloudTrail, deployments, PR history, and other sensitive configuration data. In a compliance context this is expected behavior, but the skill does not place a prominent pre-execution warning before the scripts about least-privilege credentials, data minimization, local storage protection, and the risk of exposing collected evidence if outputs are shared or stored insecurely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.