ClawHub
Back to skill

Security audit

Review Python

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Python/FastAPI code-review workflow; its commands and cross-skill references are purpose-aligned and do not show hidden execution, persistence, or data exfiltration.

Install this if you want an opinionated Python/FastAPI review workflow. It may read related review-skill instructions and run local review commands such as ruff, mypy, pytest, git diff, and grep against the target repository, so use it in repos where those checks are acceptable and ensure referenced companion skills are from sources you trust.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
Load each applicable skill (read its `SKILL.md`) before reviewing its domain.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

md
| Condition | Skill |
|-----------|-------|
| Test files changed | [pytest-code-review](../pytest-code-review/SKILL.md) |
| Pydantic-AI detected | [pydantic-ai-common-pitfalls](../../../beagle-ai/skills/pydantic-ai-common-pitfalls/SKILL.md) |
| SQLAlchemy detected | [sqlalchemy-code-review](../sqlalchemy-code-review/SKILL.md) |
| Postgres detected | [postgres-code-review](../postgres-code-review/SKILL.md) |

Static analysis

No suspicious patterns detected.