ClawHub
Back to skill

Security audit

JSON Toolkit

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward jq recipe skill for working with JSON files, with only ordinary user-run commands and no hidden execution or persistence.

Install jq only through package managers you trust, and when copying recipes that use > output redirection, choose output filenames carefully because existing files may be overwritten.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 186)May include surrounding context.

md
# The file is not valid JSON. Check for trailing commas or comments:
head -20 suspect.json

# Remove // comments (not valid JSON):
sed 's://.*$::' suspect.json | jq .

# Remove trailing commas before } or ]:

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
jq --version

# Install if missing (Debian/Ubuntu):
sudo apt-get install -y jq

# Install if missing (macOS):
brew install jq

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 177)May include surrounding context.

"jq: command not found"

bash
# Install jq:
sudo apt-get install -y jq   # Debian/Ubuntu
brew install jq              # macOS

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This file is markdown, so SQP-2 applies to omitted warnings in the skill description. Several examples redirect output into fixed filenames with >, which can overwrite existing user data, but the document does not warn users to choose safe output paths or check for existing files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.