中文 EN

Scan Report

Scan New Files

⚠ Suspicious — Risk Score 45/100
Last scan:20 hr ago Rescan
45 /100
cogdx-health
Free cognitive health check for AI agents via Cerebratech CogDx
Documentation-only skill that sends agent conversation history to an external third-party API without clear data handling policies or declared allowed-tools.
Skill Namecogdx-health
Duration29.7s
Enginepi
⚠
Use with caution
Add explicit allowed-tools declaration (network:READ), clarify data retention policies, and ensure users consent to sharing conversation outputs with the external Cerebratech service.

Findings 3 items

Severity Finding Location
Medium
Missing allowed-tools declaration Doc Mismatch
SKILL.md lacks allowed-tools metadata declaration. Despite this, the skill performs network requests to api.cerebratech.ai. The skill metadata should explicitly declare network:READ permission.
No allowed-tools field in YAML frontmatter
→ Add 'allowed-tools: Bash' or appropriate tool declaration if this skill will be implemented with code.
 SKILL.md:1
Medium
Conversation data sent to external third-party API Data Exfil
The skill sends 10-20 recent agent outputs (including user prompts and agent responses) to api.cerebratech.ai. This effectively exfiltrates conversation context to an external party without clear data retention, privacy, or consent policies documented.
POST https://api.cerebratech.ai/cogdx-health with outputs array containing prompts and responses
→ Document data handling practices, add privacy policy reference, and warn users that their prompts/responses will be sent to an external service.
 SKILL.md:32
Low
External service dependency on Cerebratech Supply Chain
The skill depends entirely on an external API (api.cerebratech.ai). If this service goes down, is compromised, or changes terms, the skill becomes non-functional. No fallback or local alternative exists.
POST https://api.cerebratech.ai/cogdx-health
→ Consider documenting reliability expectations or offering a local analysis mode.
 SKILL.md:32
ResourceDeclaredInferredStatusEvidence
Network NONE READ ✓ Aligned SKILL.md:32 POST https://api.cerebratech.ai/cogdx-health
Filesystem NONE NONE — N/A - no file operations
Shell NONE NONE — N/A - no shell execution
Environment NONE NONE — N/A - no env access
Skill Invoke NONE NONE — N/A - no skill chaining
Clipboard NONE NONE — N/A - no clipboard access
Browser NONE NONE — N/A - no browser usage
Database NONE NONE — N/A - no DB access
1 findings
🔗
Medium External URL 外部 URL
https://api.cerebratech.ai/cogdx-health
SKILL.md:25

File Tree

2 files · 5.5 KB · 155 lines
Markdown 2f · 155L
├─ ▾ 📁 references
│ └─ 📝 api.md Markdown 71L · 2.3 KB
└─ 📝 SKILL.md Markdown 84L · 3.2 KB

Security Positives

✓ No executable code present - skill is documentation only
✓ API endpoint and data format are fully documented
✓ No obfuscated code, base64 payloads, or suspicious patterns detected
✓ No credential harvesting, SSH key access, or sensitive file operations
✓ No reverse shell, C2, or direct IP-based malicious communication
✓ Skill purpose is transparent (cognitive health assessment)
✓ MIT license declared with author attribution