ClawHub
Back to skill

Security audit

Ai Code Review

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only code-review checklist for AI-authored code, with no hidden execution, persistence, or data-handling behavior found.

Install this as a review aid if you want stricter scrutiny of AI-assisted code. It is documentation-only, but users should still apply judgment before running any tests, linters, repository searches, or documentation lookups suggested during a 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
  • 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 (1)

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 · SKILL.md (reported line 68)May include surrounding context.

md
## Anti-Patterns

- [ ] Do not extend human-code trust heuristics ("clean and well-named, so probably correct") — fluency is the failure mode's costume
- [ ] Do not approve on green CI without checking whether the tests can fail
- [ ] Do not review the description instead of the diff — AI PR descriptions are confident summaries of intent, not of behaviour
- [ ] Do not reject code *for being* AI-written — review the code; provenance calibrates scrutiny, not verdicts
- [ ] Do not skip security linting because the change is small — the shortcut hides in the periphery

Static analysis

No suspicious patterns detected.