Security audit

project-delivery-intake-desk

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Markdown workflow for turning user-supplied project notes into structured project context and delivery entry outputs, with no hidden execution or data access behavior found.

Before installing, users should know this is a narrow data-formatting workflow. Use it when you want supplied project intake notes converted into structured project context or delivery-entry fields; avoid relying on it as a general project management or ledger-writing tool unless the surrounding system provides those controls.

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 (3)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The top-level description and workflow framing are broad enough that a router or agent may invoke this skill for generic 'project delivery' requests rather than only the narrowly intended intake-to-ledger transformation. That can cause unintended tool use, incorrect handling of unrelated requests, or propagation of user-supplied content into downstream structured outputs without sufficient gating.

Vague Triggers

Low

Confidence: 86% confidence
Finding: The Stage 1 activation text says to use the skill for routine project delivery work when the user asks to prepare project context, but it does not define boundaries for near-match requests. This ambiguity can lead to accidental activation on loosely related intake, planning, or summarization tasks, producing structured outputs where the skill was not actually appropriate.

Vague Triggers

Low

Confidence: 86% confidence
Finding: The Stage 2 activation wording is similarly underspecified and may fire on generic requests involving delivery records or project summaries, even when no valid project_context object is supplied. This increases the chance of incorrect tool invocation and creation of misleading ledger entries from incomplete or unrelated input.

Static analysis

No suspicious patterns detected.