ClawHub
Back to skill

Security audit

Phy Git Blame Archaeologist

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local git-history helper whose commands are disclosed and aligned with explaining why code changed.

Install this only if you are comfortable with the agent reading local git history and nearby repository files when you ask code-history questions. Prefer explicit invocations with a file, line, symbol, or directory to avoid unintended broad inspection.

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
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill metadata advertises very broad natural-language triggers like "why does this code exist" and related phrases that can appear in ordinary developer conversation. This creates a real risk of unintended invocation, causing the agent to run git-history analysis in contexts where the user did not explicitly request this skill, which can lead to unnecessary repository inspection and confusing or privacy-sensitive outputs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger section includes ambiguous phrases such as "why was this added," "who added this and why," and "explain the history of this file," which overlap with common troubleshooting or code-review dialogue. In an agent environment, this broad matching increases accidental activation risk and may cause the skill to inspect local git history without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.