ClawHub
Back to skill

Security audit

Project Memory Workflow

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed repository documentation workflow that can create or update project-memory files, with some activation ambiguity users should be aware of.

Install this if you want an agent to maintain repository memory files such as docs/PROJECT.md, docs/PROGRESS.md, docs/DECISIONS.md, and AGENTS.md. Be aware that the generic "init" trigger and implicit invocation could activate it in ambiguous initialization requests, so review generated documentation changes before keeping them.

SkillSpector

By NVIDIA
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
Confidence
92% confidence
Finding
The trigger list includes the standalone phrase "init", which is highly generic and likely to appear in normal developer requests unrelated to project-memory setup. In an agent system, this can cause unintended auto-activation of the skill, leading to unrequested repository inspection or file creation/modification beyond the user’s actual intent.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill enables implicit invocation (`allow_implicit_invocation: true`) while the manifest itself does not define strict trigger constraints or additional guardrails. Because this skill can initialize and maintain repository memory, automatic invocation could cause it to run in broader contexts than intended, potentially modifying project guidance or persisting misleading context without explicit user confirmation.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.