Security audit

百度地图地址·餐饮品牌竞对情报分析

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent restaurant competitor-analysis API guide, but it lets an inherited endpoint variable receive the user's bearer API key without validation.

Install only if you trust the publisher and service. Before using it, set DDT_OPEN_BASE explicitly to the official gotoshop-ai.com/ddtclaw endpoint, avoid running it in environments where that variable may be pre-set by someone else, and keep DDT_API_KEY scoped and rotated if misused.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:33
Finding: Unvalidated API Base URL Can Expose Bearer Credentials and Query Data
Content: View full analysis
Remediation: View remediation
&2 exit 1 } ``` The production instructions should overwrite an inherited endpoint rather than preserving it. 6. **Limit credential impact** - Use narrowly scoped and short-lived API keys where supported. - Rotate any key suspected of having been used with an untrusted endpoint. - Monitor for unexpected API usage, source locations, and quota consumption. ]]>

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep