Security audit

体测扫描工具免费版

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent body-scan purpose, but it handles sensitive full-body videos and health measurements while requesting broader agent powers and privacy assurances than the artifact supports.

Review this carefully before installing. Use it only with explicit consent from the person scanned, a verified Telegram bot and scanning API, and a sandboxed agent profile. Avoid public video URLs, confirm retention/deletion terms with the service operator, and remove or restrict exec/write permissions unless a specific reviewed implementation requires them.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:28
Finding: Unnecessary Broad Agent Tool Permissions
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:128
Finding: Insufficiently Defined Protection for Sensitive Body Videos and Health-Related Data
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill processes highly sensitive biometric and health-related content, including body videos, sex, height, and derived measurements, but does not provide a clear privacy notice describing retention, sharing, consent, security, or third-party processing. In this context, omission of explicit data-handling safeguards is dangerous because users may expose intimate personal data without understanding where it goes or how it is used.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The surrounding description presents a narrowly scoped body-scan submission and polling tool, but L051-L071 describes generic operational modes such as create/query/modify/delete, reset/import, and export/save/convert. Those statements contradict the concrete described behavior elsewhere in the file and appear to document a broader generic CRUD-style tool rather than this scan-only skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The activation scope is described using a very broad keyword list, making it likely that an agent may invoke this skill in unrelated contexts involving health, images, Telegram, or scanning. Because the skill handles sensitive body videos and personal health measurements, accidental triggering could lead to inappropriate data collection or transmission to external services.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill repeatedly states that the free version does not include history/trend comparison and does not save historical records, yet the scenario at L109-L126 shows the tool reporting "较上次减少 3.2 cm," which implies retained prior-result access or built-in historical comparison. This is an active contradiction in the documentation about what the free edition does.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The operational instructions, examples, and user-facing guidance are presented entirely in Chinese, and the skill does not state that it is intentionally limited to Chinese-speaking users or offer an alternative language option. This can be a language policy issue when a skill effectively forces one language without user opt-in or documented justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.