Security audit

Anubis Pro

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent resume-generation tool, but it unnecessarily prints full resume and job-description contents and asks users to install an unpinned package into system Python.

Review this before installing if your resume or job description contains private information. Use a virtual environment instead of the documented system Python install, avoid running it in shared/logged terminals, and treat the license check as a simple local gate rather than strong entitlement protection.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:49
Finding: Unpinned Dependency Installed into the System Python Environment
Content: View full analysis
Remediation: View remediation
--hash=sha256: ``` Then install with: ```bash .venv/bin/python -m pip install --require-hashes -r requirements.txt ``` 5. Review and pin all transitive dependencies, not only the direct dependency. 6. Avoid `--quiet` in security-sensitive installation instructions so users can inspect package sources, resolved versions, and warnings. 7. Where practical, use an organization-controlled package mirror and automated dependency integrity and vulnerability scanning. ]]>

T09 · Insecure Skill Coding Practices

Note

Location: SKILL.md:62
Finding: License Enforcement Can Be Bypassed with an Arbitrary Prefix-Matching Value
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

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill reads the full resume from RESUME_PATH and the full JOB_DESCRIPTION from environment variables, then prints both verbatim to console output. These inputs commonly contain sensitive personal and employment information, so disclosing them without a clear warning or minimization step can leak private data into logs, terminal history, shared sessions, or platform telemetry.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.