ClawHub
Back to skill

Security audit

Pdf Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PDF report generator, with a packaging flaw because the referenced templates are missing but no evidence of malicious behavior.

Install only if you are comfortable with the agent creating local .typ and .pdf files and running typst compile. The package appears security-benign, but it is incomplete as published because the promised templates are missing, so it may fail or require the agent to improvise the Typst layout.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

md
Both live next to this `SKILL.md`. Read the chosen one, then write a new

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list includes broad phrases like "generate a report," "write up a report," and especially "export these findings/results," which can apply to many non-PDF tasks in ordinary conversation. Although the file gives some clarification, these phrases are still ambiguous enough to risk unintended invocation when a user wants a different format or output.

Content

No source excerpt is available for this finding.

Unbounded Resource Access

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
- the error output,
   - the path to the `.typ` source so they can edit directly.

Do not loop indefinitely on errors.

## Reporting back

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

md
"compiled successfully" if neither is convenient),
- that the `.typ` source is kept alongside for future tweaks.

Offer to open it (`xdg-open <path>`) but do not open without confirmation.

## Quick reference: minimal Typst patterns

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill writes .typ and .pdf files and invokes a local compiler, but the user-facing description does not clearly disclose those side effects. This can lead to users authorizing the skill without understanding that it performs filesystem writes and local command execution, which is a transparency and consent issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.