Back to skill

Security audit

generate-annual-impact-report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple report-writing aid for nonprofit impact reports and does not show hidden, destructive, or credential-seeking behavior.

Before installing, understand that this skill may be invoked for nonprofit reporting tasks and may use presentation or image-generation features to create report assets. Review generated reports before publishing, especially if they include financial, donor, beneficiary, or program-impact claims.

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
  • 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
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description is broad enough that it could be invoked by ordinary reporting-related requests without clear scoping or trigger boundaries. This can cause unintended activation, leading the agent to use presentation and image-generation capabilities in contexts where the user did not explicitly request this skill, though the content itself does not appear malicious.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The suggested prompt, 'for my nonprofit business,' is highly generic and closely resembles normal user phrasing, increasing the chance of accidental or overly broad invocation. In an agent environment, ambiguous trigger text can route routine reporting requests into this skill without sufficient user intent confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.