Security audit

Security Audit by Jason

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed local security checker, but its scanner can incorrectly label risky packages as safe, so it needs review before installation.

Install only if you treat it as a lightweight helper, not as a trust gate. A clean result should not be used as proof that downloaded code is safe, especially when binaries, scripts, obfuscated strings, or unreadable files are present. Run it only on directories you intend to disclose to the scanner, and avoid --output paths that could overwrite important files.

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 (3)

T09 · Insecure Skill Coding Practices

Error

Location: audit.py:218
Finding: High-Risk Executables Can Be Misclassified as Safe When Decoy Source Code Is Present
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: audit.py:94
Finding: Destructive String Removal Allows Embedded Payloads to Evade Pattern Detection
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: audit.py:109
Finding: Suppressed Scan Exceptions Cause Incomplete Audits to Be Reported as Clean
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 86% confidence
Finding: The skill documents workflows that read from and write reports to the filesystem, but it does not declare any explicit tool scope such as permissions or allowed-tools. In an agent environment, undeclared file capabilities weaken policy enforcement and make it harder to constrain or review what the skill may access, especially because this skill is intended to inspect untrusted external resources.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The README contains the Chinese term "疑似" inside an example output line, introducing a language/locale inconsistency in user-facing content. The file does not offer language selection or explain that mixed-language output is intentional or region-specific, which can violate language-consistency policy expectations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This code performs a file write based on user input via --output, but the write path has no confirmation prompt and no nearby user-facing disclosure that an existing file may be overwritten. Although saving a report is part of the tool's function, the code itself does not warn about this potentially data-affecting operation.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: audit.py:41