Security audit

Shadows Python Sensei

Security checks for vulnerabilities and agentic risk

Overview

This Python review skill is coherent and disclosed, with only a minor dependency-installation caution.

Install only in repositories where you are comfortable letting an agent edit Python files and, if tests are run, execute project test code. Use a virtual environment and prefer pinned or locked tool dependencies instead of copying floating `pip install` examples blindly.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:31
Finding: Unpinned Third-Party Package Installation Instructions
Content: View full analysis
Remediation: View remediation
ruff== ``` 4. Maintain a lock file or requirements file containing cryptographic hashes, and install it using hash enforcement: ```bash python -m pip install --require-hashes -r requirements-tools.txt ``` 5. Use an explicitly configured trusted package index or an internally controlled artifact repository rather than inheriting an arbitrary global `pip` configuration. 6. Review and lock transitive dependencies, not only the top-level packages. 7. Update the offline-operation claim to clarify that package installation requires network access unless dependencies are already supplied through a trusted local source. 8. Preserve the existing warning about running project tests only in trusted repositories or sandboxed environments, because `pytest` imports and executes repository-controlled Python code. ]]>

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