Back to skill

Security audit

Flow PDF Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill generates local PDF files from user-provided structured data, with no evidence of hidden access, persistence, exfiltration, or unsafe install behavior.

Before installing, consider that the helper script writes to the output path you provide and may embed local images from paths in your JSON. Review generated PDFs for language labels if you need non-German metadata text.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest description says to use the skill when a user wants to "create, export, or save content as a PDF file," which is broad enough to overlap with common requests and does not define exclusions or tighter scope boundaries. Although several specific trigger phrases are listed, the surrounding activation condition remains ambiguous about when this skill should or should not be invoked.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The generated PDF metadata line uses the hard-coded labels "Autor" and "Datum", which forces German output regardless of user preference. This is a natural-language locale policy issue because the file provides no opt-in, fallback, or documentation that the skill is intentionally German-only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The trigger list includes German phrases alongside English ones, but the file does not explain whether multilingual triggering is optional, user-selected, or constrained to a specific locale. This can create a language-policy issue because the skill embeds locale-specific activation behavior without documenting user choice or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file includes a full example whose title, headings, and list items are written in German, but it does not indicate that the language is optional or region-specific. Under the policy, natural-language instructions or examples that effectively impose a specific language without user opt-in should be flagged.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.