ClawHub
Back to skill

Security audit

Git Blame

Security checks for vulnerabilities and agentic risk

Overview

This is a local, read-only git history audit skill with no hidden execution, persistence, or data exfiltration behavior found.

Install only where it is acceptable for the agent to read local git history and report author/commit metadata. Use explicit targets like /git-blame-audit path:line to avoid accidental broad audits.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: Git Blame Auditor
description: Production code audit via git blame. Natural language risk analysis — overtime commits, scattered changes, no-PR-review merges, and impact domain tracing for every suspicious line.
license: MIT-0
homepage: https://github.com/harry
metadata:
  author: Harry Jiang
  version: "1.0.0"
  tags:
    - git
    - blame
    - audit
    - security
    - code-review
    - risk-analysis
    - developer-tools
---

# Git Blame Auditor

> **Audit perspective git blame.** Not "why does this code exist?" — but "**is this code safe?**"

You're in a security review. A line catches your eye — `e

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases include broad natural-language requests like 'is this code risky' and 'who last touched this and is it safe', which are plausible in ordinary conversation and could cause unintended activation of the skill. In an agent environment, overbroad invocation increases the chance of the skill running on unrelated prompts and exposing repository metadata or influencing downstream analysis without explicit user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.