Security audit

Nano PDF工具（免费版）

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward PDF helper skill with no evidence of hidden or malicious behavior, though its dependency and edit-safety guidance could be clearer.

Before installing, treat this as a local PDF automation helper: review output paths, avoid in-place edits unless you have a backup, and install Python dependencies in an isolated environment with pinned versions where possible.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:142
Finding: Unpinned Third-Party Dependencies Allow Mutable Supply-Chain Code
Content: View full analysis
Remediation: View remediation
reportlab== ``` 3. Generate a lock file that also fixes transitive dependency versions. 4. Require package hashes, such as through `pip install --require-hashes -r requirements.txt`. 5. Use an explicitly trusted package index and prevent fallback to untrusted or user-controlled indexes. 6. Install dependencies inside an isolated virtual environment or restricted container rather than the Agent's global Python environment. 7. Run dependency vulnerability and provenance checks before releases and update pins through a controlled review process. 8. Execute PDF processing with least privilege, restricting filesystem and network access to the minimum required for user-approved input and output files. ]]>

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Behavioral ASTexec() Call, eval() Call, Dynamic Import
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger phrases are generic requests such as reading a PDF, creating a PDF, or rotating a page—common tasks that may appear in ordinary conversation. In an agent ecosystem, overly broad activation patterns can cause accidental invocation of a skill with read/exec/write capabilities, increasing the chance of unintended file access or modification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill advertises PDF creation and page modification operations but does not warn about overwrite, destructive edits, or data-loss scenarios. Because the skill also exposes write and exec capabilities, users may unintentionally alter or replace files without adequate notice or confirmation.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill states that no API key is required while also declaring an LLM API as a required dependency. This inconsistency can mislead users about external service use, trust boundaries, and possible data transmission to provider-backed model infrastructure, which is a security-relevant transparency failure.
Content: No source excerpt is available for this finding.