ClawHub
Back to skill

Security audit

memory-digest

Security checks for vulnerabilities and agentic risk

Overview

This skill reads an agent's memory logs to generate a digest, and that behavior is clearly disclosed and aligned with its purpose.

Install this only if you are comfortable letting the skill read your agent's local memory logs and summarize them. Use explicit digest/report requests, review pending items before acting on them, and only add cron scheduling if you want recurring reports saved or delivered automatically.

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
Confidence
88% confidence
Finding
The README advertises broad natural-language trigger phrases such as weekly digest, what did my agent do, 记忆周报, and 述职报告 for automatic skill activation. In an agent environment, overly generic triggers can cause this skill to run unintentionally on normal conversation, leading to unnecessary access to memory logs and possible disclosure of sensitive historical activity in contexts where the user did not explicitly request a digest.

Static analysis

No suspicious patterns detected.