ClawHub
Back to skill

Security audit

orca-replay

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent and purpose-aligned, with clear warnings about replay, external side effects, uploads, and cost.

Before installing, understand that this skill can guide an agent to replay recorded runs and compare models. Use worktree/container isolation for replay, review commands before rerunning them, and only compare models after approving provider disclosure, side effects, and cost.

SkillSpector

By NVIDIA
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 (3)

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.

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.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The tools table labels `orca_replay` as 'offline, free, repeatable' even though the body clearly states replay re-executes shell commands, may access the network through subprocesses, and is not a sandbox. This contradiction can cause an agent or operator to rely on the summary and trigger real external side effects without the approvals and isolation the earlier sections require.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.