T09 · Insecure Skill Coding Practices
- Location
SKILL.md:26- Finding
Malformed curl Command Places JSON-RPC and Potentially Sensitive User Content in an Authentication Header
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This is a simple approval-office connector skill whose sensitive token use is disclosed and purpose-aligned, but its examples need safer credential and request-body guidance.
Install only if you trust the local approval service at 127.0.0.1:7861 and have an appropriate Beyond-Token. Keep the token out of shell history, logs, screenshots, and shared documents, and fix the curl example to send JSON in the request body with a Content-Type header before using it for real approval or leave data.
SKILL.md:26Malformed curl Command Places JSON-RPC and Potentially Sensitive User Content in an Authentication Header
The documentation mandates use of a Beyond-Token authentication header but provides no guidance on secure handling, storage, redaction, or rotation of that credential. In an enterprise approval and leave-management context, this increases the chance users expose reusable tokens in shell history, screenshots, logs, or shared docs, which could enable unauthorized access to workflow and employee data.
The curl examples send authentication material over plain HTTP to a local service without any warning about transport-security assumptions. Even if bound to 127.0.0.1, local plaintext transport can still be exposed through misconfiguration, port forwarding, malware, local proxies, container networking, or copy-pasted adaptation to non-local deployments, risking token theft and unauthorized approval actions.