Back to skill

Security audit

hello-env

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because a scanner reports a serious command execution flaw in its environment-check script, though the results do not establish malicious intent.

Treat this as a review decision, not a finding that the author acted maliciously. Before installing, consider whether you trust the project content the environment check may inspect and whether you can avoid running it against untrusted projects. The scan reports complete file coverage for Skillspector, but its behavioral AST, taint-tracking, and bundled-execution analyzers were not applicable; that limits what this scan establishes.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/check-env.sh
Finding

Project-controlled snapshot content can execute commands through Bash arithmetic

Content
View full analysis

Impact

An attacker-controlled project snapshot can execute arbitrary commands with the health-check process's privileges. No malicious payload is present in the audited package; this is an exploitable coding defect, not evidence of author intent.

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.