ClawHub
Back to skill

Security audit

orca-replay

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned and unusually explicit about replay, upload, cost, and side-effect risks, though users should treat replay and compare operations as real executions rather than harmless viewing.

Before installing, confirm you trust the external orcareplay npm package and MCP server. Before using replay or compare, review what the recorded run did, use worktree/container isolation where appropriate, and approve any provider upload, spending, or external side effects explicitly.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The tools table summarizes orca_replay as 'offline, free, repeatable', but the body of the skill clearly states that replay re-executes shell commands and may reach external networks or mutate systems outside the worktree. This inconsistent shorthand can mislead an agent or operator into treating replay as harmless, increasing the chance of unintended destructive actions or data egress.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Describing orca_replay as 'offline' in the summary is materially misleading because the same document states subprocesses can still access the network and alter external systems. In this skill context, users may invoke replay specifically to investigate prior runs, so a misleading safety label can directly cause risky execution under false assumptions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.