T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:43- Finding
Matomo Authentication Token Exposed in URL Query String and Process Arguments
- Content
View full analysis
- Remediation
View remediation
Security audit
Matomo Analytics
Security checks for vulnerabilities and agentic risk
Overview
The skill is mostly coherent for Matomo analytics, but its documented API pattern can expose the Matomo token in command lines and logs.
Review before installing if your Matomo token has broad permissions. Use a dedicated least-privileged token, avoid pasting real tokens into chat or shell commands, prefer secure environment or keychain storage, and be aware that ~/matomo/ may store site names, IDs, priorities, templates, and cached analytics context.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 70% confidence
- Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- Content
md ## Connection matomo_url: (URL when provided) token_ref: (keychain/env reference, never actual token) ## Priorities <!-- What metrics matter to them -->
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 70% confidence
- Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- Content
md ## Connection matomo_url: (URL when provided) token_ref: (keychain/env reference, never actual token) ## Priorities <!-- What metrics matter to them -->
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This markdown file documents obtaining a personal
token_authand embedding it directly in API requests, which involves handling sensitive credentials. The file does not include any warning about keeping the token secret, avoiding shell history exposure, or not sharing commands containing the token.- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill directs the agent to persist site names, idSite mappings, business-priority metrics, and a default site in a local file without instructing the user to consent to that storage or warning that this metadata may be sensitive. Even though it avoids storing the API token itself, this contextual business data can reveal internal analytics structure, tracked properties, and operational priorities, which increases privacy and reconnaissance risk if the local machine, home directory, backups, or logs are exposed.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This markdown file describes activation in general terms like 'query Matomo analytics, generate reports, track goals, or manage their self-hosted analytics' without specifying concrete trigger phrases, scope limits, or negative examples. That ambiguity could cause the skill to be invoked for generic analytics-related requests beyond the intended Matomo-specific context.
- Content
Static analysis
No suspicious patterns detected.