Security audit

Review Verification Protocol

Security checks for vulnerabilities and agentic risk

Overview

This skill is a code-review checklist, but it gives broad mandatory instructions that can narrow reviews and suppress newly found issues.

Install only if you want all code reviews to follow this checklist. Be aware that it can make the agent omit newly discovered issues during re-review and treat some review output rules as mandatory rather than advisory.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:3
Finding: Mandatory Skill Instructions Hijack Review Scope and Verdict Behavior
Content: View full analysis
The artifact is the only source of truth. **Never** infer what you are reviewing from the branch name, the working directory, surrounding files, or recollection. If your mental model differs from the freshly read source, **the source wins.** A verdict issued without a same-turn echo of its target is invalid — emit the echo first, or do not emit the verdict. ``` Additional verdict-control instructions: ```markdown **These are NOT review blockers.** They should be noted for the author's awareness but must not appear in the actionable issue count. The Verdict should ignore informational items entirely. ``` ```markdown 7. If this is a re-review: ONLY verify previous fixes. Do not introduce new findings. ``` ### Technical Analysis The skill is marked `user-invocable: false`, while its description directs the agent to load it before reporting any code-review findings. Once loaded, it uses mandatory language ...[truncated 2631 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.