T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/oura-briefing.sh:14- Finding
Oura Bearer Token Exposed Through Process Arguments and Shell History
- Content
View full analysis
- Remediation
View remediation
Security audit
Oura Briefing
Security checks for vulnerabilities and agentic risk
Overview
The skill does what it claims, but it handles an Oura health-data token in ways that can expose it locally and gives too little privacy guidance for sensitive health metrics.
Install only if you are comfortable letting the skill retrieve and summarize Oura health data. Prefer OURA_API_TOKEN over --token, avoid running it where command history or process arguments are logged, and consider rotating the token if you previously passed it on the command line.
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)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 93% confidence
- Finding
The skill explicitly instructs users to handle a personal access token and also supports passing it via a --token CLI argument, which is especially risky because command-line arguments are often exposed through shell history, process listings, logs, and agent traces. Since the token grants access to private health data, leakage could enable unauthorized retrieval of sensitive user information.
- Content
Setup
Set your Oura Personal Access Token:
bash export OURA_API_TOKEN="your_token_here"
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 88% confidence
- Finding
The skill instructs the agent to execute a shell script but does not declare any explicit tool scope or allowed-tools boundary in the skill manifest. That creates ambiguity about what execution capabilities are intended and can lead to over-broad shell access in environments that rely on manifest-declared permissions for containment.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This skill processes highly sensitive health data and uses an API token, but the documentation provides no privacy notice, retention guidance, or warning about exposing personal metrics in agent outputs or logs. In practice, users or agents may disclose sleep, recovery, or token data into shared transcripts, terminals, or telemetry without informed consent.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
sh exit 1 fi API="https://api.ouraring.com/v2/usercollection" HDR="Authorization: Bearer $TOKEN" # Fetch data
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The script sends sleep, readiness, and activity requests to the Oura API, which involves transmitting sensitive personal health data. While the file header states it fetches Oura data, the script provides no runtime warning, confirmation, or explicit user-facing notice about the network access and privacy implications.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The script reads a bearer token from the OURA_API_TOKEN environment variable, which is a sensitive credential source. Although it errors if the token is absent, there is no disclosure or warning to the user that the script consumes a credential from environment variables or that passing --token on the command line may expose it in shell history or process listings.
- Content