Security audit

Grant Writing Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only grant-writing coach with no code execution, persistence, credential use, or hidden behavior.

Installers should expect this skill to help draft and plan grant applications. Review funder deadlines, eligibility, and budget rules independently because grant requirements change and the skill’s advice is general guidance, not an authoritative filing system.

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: 88% confidence
Finding: The listed 'Basic invocation' phrases such as 'Help me find funders for [project / topic]' and 'Build a logic model for my program' are natural, general requests that could plausibly appear in ordinary conversation. The file does not provide negative examples or explicit boundaries clarifying when these phrases should or should not activate the skill.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.