ClawHub
Back to skill

Security audit

Local File Processor

Security checks for vulnerabilities and agentic risk

Overview

The skill describes ordinary local file-processing tasks with user-selected targets and disclosed safety controls, with no hidden persistence or data exfiltration in the inspected artifact.

Before installing, confirm you trust the Homebrew dependencies and use --dry-run first on important folders. Avoid --force or --overwrite unless you have backups and intentionally want those file changes.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Self-Modification

High
Category
Rogue Agent
Content
## Safety Model

- **No overwrite by default** for move/convert operations.
- Use `--overwrite` to explicitly replace existing files.
- Destructive operations require confirmation unless `--force`.
- `--dry-run` works for all write/delete operations.
- File scanning uses null-delimited handling for safer filenames.
Confidence
85% confidence
Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- `--dry-run` — Preview changes, no files modified/deleted
- `--overwrite` — Allow replacing existing target files (default is no overwrite)
- `--force` — Skip confirmation prompts for destructive actions
- `--verbose` — Verbose output

## Commands
Confidence
85% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.