T09 · Insecure Skill Coding Practices
- Location
SKILL.md:301- Finding
Untrusted MCP Card Content Is Injected into Model Conversations
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent MCP Apps host-development guide, but it recommends under-scoped card permissions and persistence that can let untrusted cards influence model turns or retain sensitive card data.
Review this skill carefully before installing. It is most appropriate for developers working on MCP Apps host code, but generated changes should be tightened: require explicit authorization for card-originated model turns, separate card data from user instructions, use per-card or per-tool allowlists instead of broad server-wide permission, restrict CSP domains and forms, avoid durable localStorage for sensitive payloads, and prefer a pinned or manually reviewed installation path.
SKILL.md:301Untrusted MCP Card Content Is Injected into Model Conversations
SKILL.md:258Overly Permissive Card CSP Enables Unauthorized Network Disclosure
SKILL.md:446Sensitive MCP Card Payloads Are Persisted in localStorage Across Sessions
README.md:56Recommended Installation Executes an Unpinned Third-Party Package
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
The skill content is written entirely in Chinese starting with the title at L010 and continuing throughout the document, while the manifest description at L003 is in English and does not state that the skill is China-specific or requires Chinese. This creates a language-policy issue because users are not given an opt-in or alternative language choice.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -s --max-time 10 "<base_url>/chat/completions"
-H "Authorization: Bearer "
-d '{"model":"","messages":[{"role":"user","content":"hi"}],"max_tokens":5}'
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.