Security audit

review-chamber

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PR-review memory tool, but it can automatically persist and resurface untrusted PR discussion content without clear trust-boundary safeguards.

Install only if you are comfortable with PR review findings and discussion context being retained and resurfaced later. Use it with a workflow that treats captured PR text as quoted historical data, requires trusted review before permanent storage, records provenance, and provides deletion or reapproval for stale or poisoned entries.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
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)

T02 · Agent Memory Poisoning

Warning

Location: modules/capture-workflow.md:208
Finding: Persistent Storage and Automatic Surfacing of Untrusted PR Content
Content: View full analysis
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.