Security audit

Code Quality Paid

Security checks for vulnerabilities and agentic risk

Overview

The skill is a code audit helper, but its instructions can run an untrusted project-local audit.py with agent permissions.

Review this skill before installing. Use it only in a sandbox or disposable checkout, do not run project-local audit.py from untrusted repositories, and prefer a verified scanner path with reports written to a controlled directory. Generated reports may contain sensitive code-derived findings.

A.I.G

Vulnerability Patterns

Tool Hijacking and SpoofingModifies or replaces tools so legitimate-looking calls execute attacker logic
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T07 · Tool Hijacking and Spoofing

Error

Location: SKILL.md:150
Finding: Execution of an Untrusted Project-Supplied audit.py Script
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:344
Finding: Unpinned Third-Party Package Installation Instruction
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill describes full-project batch auditing, dependency review, and multi-format report generation, but does not clearly warn that this may read the entire repository, inspect potentially sensitive source/configuration files, and write report artifacts containing code-derived findings. In an agent environment, this increases the risk of unintended data exposure, oversized scans, or persistence of sensitive details into SARIF/HTML/JSON outputs.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill includes a natural-language invocation phrase asking to perform a comprehensive security audit of the current project and generate reports. Because this trigger is broad and maps directly to repository-wide analysis and file generation, it can activate on ordinary user requests and cause the agent to read large amounts of code and write artifacts without an explicit confirmation step.
Content: No source excerpt is available for this finding.