ClawHub
Back to skill

Security audit

svn-code-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SVN code-review helper with no embedded code, persistence, credential handling, or network behavior.

Install this if you want an opinionated SVN review workflow. Expect it to invoke a code-review subagent frequently unless you choose to use it only at explicit checkpoints, and pass only the diffs and requirements needed for review.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is broadly scoped to routine software-development moments such as completing tasks, implementing features, and pre-merge checks. That can cause the skill to activate across many normal interactions, increasing the chance of unnecessary delegation, review-loop spam, or disclosure of work context to another agent when not strictly needed. In this context the skill is not overtly malicious, but the broad trigger surface makes misuse or over-invocation more likely.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · code-reviewer.md (reported line 104)May include surrounding context.

md
- Give clear verdict

**DON'T:**
- Say "looks good" without checking
- Mark nitpicks as Critical
- Give feedback on code you didn't review
- Be vague ("improve error handling")