Back to skill

Security audit

RustChain Bounty Hunter-v2-1

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious, but it asks the agent to autonomously change code and push to a fork without enough review or consent boundaries.

Install only if you are comfortable with an agent making bounty-related code changes and preparing remote repository updates. Before using it, require the agent to work on a dedicated branch, show a diff, run tests, and ask for explicit approval before any push or PR-related action.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill states it will 'handle the coding, testing, pushing to your fork, and prepare the PR' but does not warn the user that it may perform external actions affecting their codebase and remote repository. In this context, omission of a clear warning and consent model is dangerous because it can normalize autonomous code submission, potentially introducing insecure code, unwanted changes, or reputational and supply-chain risk through premature pull requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The usage text uses a very broad trigger ('Just tell me which bounty you want to do next') that can cause the skill to activate on loosely related user requests without clearly bounded scope or explicit confirmation. Because the skill is described as handling coding, testing, pushing to a fork, and preparing a PR, an overbroad invocation increases the chance of unintended repository actions or autonomous software changes on the user's behalf.

Content

No source excerpt is available for this finding.