Security audit

Json Linter

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward JSON linter, but its recursive scan can follow symlinks outside the chosen folder and may recurse through symlink cycles.

Install only if you are comfortable with it reading JSON files reachable from the directory you scan. Avoid running it on workspaces containing untrusted symlinks until it is hardened to skip symlinks or enforce a canonical scan-root boundary and recursion limits.

A.I.G

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

Warning

Location: index.js:8
Finding: Directory Symlink Traversal Allows Scan-Root Escape and Recursive Denial of Service
Content: View full analysis
/some/readable/directory`; or - A cyclic link, such as a descendant directory linking back to one of its ancestors. 3. A user or agent invokes the skill against the workspace. 4. `fs.statSync()` follows the link ...[truncated 1196 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.