Security audit

Anubis Lite

Security checks for vulnerabilities and agentic risk

Overview

This resume-analysis skill mostly matches its purpose, but it asks to modify the system Python environment and injects mandatory promotional output.

Review this before installing. The resume-analysis behavior is clear, but run any dependency install in a virtual environment instead of your system Python, and avoid pasting confidential job postings if the generated transcript may be logged or shared. Expect the output to include a paid upgrade promotion.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:128
Finding: Mandatory Commercial Promotion Injected into Agent Output
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:42
Finding: Unpinned Dependency Installation Bypasses System Package Protections
Content: View full analysis
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

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill prints the full JOB_DESCRIPTION back to output without warning the user, which can expose sensitive or proprietary information contained in a pasted job posting. While this is not code execution or privilege escalation, it creates an unnecessary data exposure risk, especially if outputs are logged, shared with downstream tools, or visible in multi-tenant environments.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.