ClawHub
Back to skill

Security audit

Propmt Archeologist

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-writing helper that reads the current conversation to turn a task into a reusable prompt, with no code execution, external access, or persistence.

Install this if you want help turning conversations or rough task descriptions into reusable prompts. Be aware that ambiguous requests like "what did I just do?" may trigger it, so avoid invoking it around sensitive conversation context unless you are comfortable having that context summarized into a prompt shown in the chat.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly says to always trigger on broad, ambiguous phrases like "save this workflow" or "what did I just do?" even when the word "prompt" is absent. That can cause over-activation on normal conversation, leading the agent to invoke the skill in contexts the user did not intend and increasing the chance of context misinterpretation or unintended prompt extraction from prior conversation content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.