Back to skill

Security audit

xinywa Coding Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed coding workflow for careful repository changes, with persistent indexing and logs that are purpose-aligned but worth understanding before use.

Install this if you want a structured workflow for complex repository changes. Be aware that it keeps local indexes and run logs under /home/vibe/aksclaw-data, so avoid using it on repositories where retaining local metadata is not acceptable.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation condition "Triggered when BLOCKED" is underspecified and can match many unrelated situations, making unintended invocation likely. In an agent workflow, ambiguous recovery triggers can cause the system to enter recovery mode prematurely, alter execution flow, and perform unnecessary retries or context changes that mask the real failure state.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The routing rule 'ONLY trigger skill for COMPLEX_CODE_TASK' relies on broad, informal categories that are not operationally defined. Ambiguous activation boundaries can cause the skill to be invoked for tasks outside its intended scope or skipped when needed, which is risky for a security-sensitive code-change workflow because misrouting can bypass safer handling paths.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file describes the skill's purpose and when to check it using broad phrases like 'Ensure execution is' and 'After each step' without specifying the exact contexts, triggers, or exclusions for invoking the skill. Because it lacks narrow trigger phrases or negative examples, it could be applied to many ordinary situations and cause unintended invocation.

Content

No source excerpt is available for this finding.