Back to skill

Security audit

Grant Application Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward UK grant-writing prompt skill with no code, persistence, portal access, or credential use.

Before installing, users should understand this is UK-oriented drafting help. They should verify funder guidance, statistics, legal compliance, budget figures, and any current programme details before submitting an application.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README states that all output uses UK English and UK regulatory/framework references. This is a natural-language locale policy constraint that applies universally to the skill, but the description does not offer a user choice or make the locale limitation optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction "UK English throughout" imposes a fixed language/locale requirement as a universal rule. This is a natural-language policy concern because it does not offer users a locale choice or clearly frame the restriction as optional based on user preference.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description says to use the skill when someone needs to "apply for a grant, write a funding proposal, or prepare a bid," which is broad and lacks explicit trigger boundaries or exclusion conditions. In a user-invocable skill manifest, this can cause unintended activation for general writing or proposal-support requests beyond the intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The listing states 'UK-specific: UK English' and frames UK conventions as automatically handled, which indicates the skill may force a specific language/locale. The file does not mention any user opt-in or ability to choose another locale, which falls under the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.