Scan Report
5 /100
fund-advisor
场外公募基金配置顾问 Agent Skill,具备10年实战投资经验的资深理财经理角色
Pure documentation-only skill with no executable code, scripts, or binary files. All 7 files are Markdown documentation describing a fund advisor AI agent concept.
Safe to install
No action required. This is a documentation-only skill package with no security concerns.
Findings 1 items
| Severity | Finding | Location |
|---|---|---|
| Low | Loose version constraints in declared dependencies | SKILL.md:14 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | NONE | NONE | — | No file read/write operations; SKILL.md declares no filesystem access |
| Network | NONE | NONE | — | No network calls declared or implemented; external data access via integrated sk… |
| Shell | NONE | NONE | — | No shell execution, no subprocess calls, no scripts found |
| Environment | NONE | NONE | — | No environment variable access documented or implemented |
| Skill Invoke | READ | NONE | ✓ Aligned | Mentions web-search, document-generation, knowledge, feishu-message skill integr… |
| Clipboard | NONE | NONE | — | No clipboard access |
| Browser | NONE | NONE | — | No browser automation |
| Database | NONE | NONE | — | No database access; mentions /tmp storage for data but no DB operations |
File Tree
7 files · 77.4 KB · 3020 lines Markdown 7f · 3020L
├─
▾
examples
│ └─
usage-examples.md
Markdown
├─
▾
references
│ ├─
agent-best-practices.md
Markdown
│ ├─
data-storage.md
Markdown
│ ├─
skill-integration.md
Markdown
│ └─
tool-development.md
Markdown
├─
README.md
Markdown
└─
SKILL.md
Markdown
Dependencies 3 items
| Package | Version | Source | Known Vulns | Notes |
|---|---|---|---|---|
coze-coding-dev-sdk | >=0.5.11 | SKILL.md declared | No | No upper bound; only declared, not installed or executed |
langchain | >=1.0 | SKILL.md declared | No | No upper bound; only declared, not installed or executed |
langgraph | >=1.0 | SKILL.md declared | No | No upper bound; only declared, not installed or executed |
Security Positives
✓ No executable scripts, code files, or binaries — 100% documentation
✓ No credential harvesting or sensitive path access
✓ No network exfiltration patterns (no curl|bash, wget|sh, eval, atob)
✓ No hidden functionality — documentation and declared capabilities are consistent
✓ No base64-encoded payloads or obfuscated code
✓ No suspicious IOC indicators (pre-scan found zero IOCs)
✓ Uses /tmp for data storage as documented, no exfiltration paths
✓ Includes investment risk disclaimers and合规性 guidance