ClawHub
Back to skill

Security audit

project-ops-protocol

Security checks for vulnerabilities and agentic risk

Overview

This is a project-management workflow skill that keeps shared project notes and ledgers, with no hidden code, automatic execution, or data-exfiltration behavior found.

Install this if you want a structured workflow for multi-session projects. Expect the agent to create, read, and update project Markdown records such as ledgers, alignment boards, relay notes, and handbooks. The broad trigger wording may make it appear in general project-planning discussions, so users should invoke it when they actually want this operating protocol.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (4)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 13)May include surrounding context.

md
## What you get

- **Four layers**: Plan (layered battle map + honest watchlist) → Execute (measure first, reuse before rebuild) → Sync (append-only alignment board + milestone heartbeats) → Memory (relay note + handbook-first rules).
- **Seven standard artifacts** with one job each and a write rule (battle map, release ledger, topic ledger, alignment board, relay note, retrospective, handbook).
- **Eight hard rule cards** that prevent the common failure modes (lost context, silent overwrites, duplicated work, secret leakage, publishing too early).
- **LLM-as-judge quality rubric** (5 dimensions, ≥0.80 pass) plus a 30-second self-check for anything that goes public.
- **Day-1 and wrap-up checklists** you can paste into any project.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 20)May include surrounding context.

Install (as an agent skill)

Copy the SKILL.md into your agent's skills directory (e.g. ~/.workbuddy/skills/project-ops-protocol/SKILL.md, or .claude/skills/...), or clone this repo and point your skill loader at the SKILL.md.

bash
git clone https://github.com/zhaoxinghua09-cell/project-ops-protocol

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 20)May include surrounding context.

Install (as an agent skill)

Copy the SKILL.md into your agent's skills directory (e.g. ~/.workbuddy/skills/project-ops-protocol/SKILL.md, or .claude/skills/...), or clone this repo and point your skill loader at the SKILL.md.

bash
git clone https://github.com/zhaoxinghua09-cell/project-ops-protocol

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad operational terms such as "alignment," "wrap-up," "retrospective," and "operating model," which are common in many unrelated conversations. This can cause unintended activation of the skill in contexts where the full project-ops protocol is not appropriate, leading to prompt hijacking of the workflow, user confusion, or unnecessary exposure of internal project structure/process instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.