Back to skill

Security audit

Review Feedback Schema

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only schema for recording code review feedback and does not include hidden execution, persistence, credential access, or destructive behavior.

Before installing, expect this skill to guide agents in recording code review outcomes and rationales in a structured CSV format. Review any chosen feedback-log destination in your environment, since entries may include repository file paths and issue rationales, but the skill itself is documentation-only and does not execute code.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 186)May include surrounding context.

md
1. **Aggregate by rule_source**: Identify which rules have high REJECT rates
2. **Analyze rationales**: Find common themes in rejections
3. **Update skills**: Add exceptions, clarifications, or verification steps
4. **Track impact**: Measure if changes reduce rejection rate

See the [review-skill-improver](../review-skill-improver/SKILL.md) skill for the full analysis workflow.