ClawHub
Back to skill

Security audit

Shoofly Plugin Scan

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small pre-install plugin scanner guide and the flagged sensitive paths are examples of patterns it looks for, not instructions to read credentials.

Before using it, verify that `shoofly-plugin-scan` comes from a trusted source and point it only at plugin directories you intend to review. The skill text itself is coherent and does not show hidden or destructive behavior.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
1. **Credential patterns** — API keys (sk-*, ghp_*, AKIA*), private keys
2. **Obfuscated code** — long hex/base64 strings, eval(), Function() constructor
3. **Unusual network calls** — URLs not in the trusted allowlist
4. **Sensitive path access** — ~/.ssh, ~/.aws, ~/.gnupg, /etc/passwd, credentials
5. **Exec patterns** — child_process.exec with variable args, shell: true

## Exit codes

Static analysis

No suspicious patterns detected.