Back to skill

Security audit

reverse-engineer-anything

Security checks for vulnerabilities and agentic risk

Overview

The scanners found mutable Docker image references in this reverse-engineering skill, so ClawScan marked it suspicious for review; the scan evidence is incomplete.

Before installing, consider whether you trust the image source and can verify and pin the Docker image to a reviewed SHA-256 digest. The scanners inspected all three listed components, but the overall analysis is partial because five path-like references could not be resolved, so the evidence does not establish that every relevant item was assessed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (3)

Docker image referenced without tag or digest: 'docker run you'.

Medium
Category
MCP Rug Pull
Confidence
75% confidence
Finding

Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Content

No source excerpt is available for this finding.

Docker image referenced without tag or digest: 'docker run -d'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

Although the detector matched command options rather than the image argument, the complete command uses the mutable image tag 'psyb0t/reverse-engineer-anything:latest', not an immutable digest. A compromised or unexpectedly changed image could read mounted analysis targets and exfiltrate them over the server container's available network; the read-only mount and dropped capabilities reduce host modification risks but do not protect target confidentiality.

Content

No source excerpt is available for this finding.

Docker image referenced without tag or digest: 'docker run --rm'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The command options are not an image reference, but the actual image argument resolves by default to the mutable 'psyb0t/reverse-engineer-anything:latest' tag. An unexpectedly changed or compromised image could read mounted targets and falsify analysis output; network isolation limits direct exfiltration by default, while the optional network mode increases exposure.

Content

No source excerpt is available for this finding.