T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:19- Finding
External Embedding Configuration May Expose Sensitive Session Transcripts
- Content
View full analysis
- Remediation
View remediation
Security audit
Memory Setup (Jack)
Security checks for vulnerabilities and agentic risk
Overview
The skill is coherent for setting up memory search, but its recommended defaults can index private memory files and past chats through cloud embedding providers without clear privacy warnings.
Install only if you are comfortable configuring persistent memory. Before enabling the recommended settings, review memory files and old session transcripts for secrets, credentials, personal data, and confidential project details. Prefer the local provider or limit sources to curated memory files when private or regulated data should not leave your machine.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill explicitly encourages indexing MEMORY.md, memory/*.md files, and past session transcripts, which can contain highly sensitive personal, project, or confidential business information. Because it presents this as a straightforward setup flow without any privacy warning, retention guidance, or data minimization advice, users may unknowingly ingest sensitive data into searchable memory stores and potentially third-party embedding providers.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill tells users to set VOYAGE_API_KEY and OPENAI_API_KEY and to use hosted embedding providers, but it does not warn that indexed memory content may be transmitted to external services or that API keys must be handled carefully. This omission can lead to accidental disclosure of sensitive workspace data to third parties and poor secret-management practices during setup.
- Content
Static analysis
No suspicious patterns detected.