T03 · Remote Payload Retrieval and Execution
Error
- Location
SKILL.md:21- Finding
Automatic Retrieval and Execution of Mutable Cloud Skills
- Content
View full analysis
- Remediation
View remediation
Security audit
OpenSpace Delegate Task
Security checks for vulnerabilities and agentic risk
Overview
The skill is openly designed to delegate work to OpenSpace, but its defaults allow cloud skill import/execution and public skill upload with too little user review.
Install only if you are comfortable with OpenSpace handling delegated tasks and potentially using cloud skills. Before use, prefer local-only search, disable automatic cloud imports, review any evolved skill directory for secrets or internal details, and require explicit approval before uploading anything publicly.
Vulnerability Patterns
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- 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
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)
T09 · Insecure Skill Coding Practices
Error
- Location
SKILL.md:86- Finding
Potential Public Disclosure Through Unapproved Skill Uploads
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)
Missing User Warnings
High
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill describes cloud/local search behavior but does not clearly warn that task content, queries, metadata, or derived artifacts may be transmitted to external services when cloud search is used. Users or calling agents may therefore disclose sensitive operational, codebase, or business information without informed consent.
- Content
Missing User Warnings
High
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The upload guidance encourages public sharing of evolved or fixed skills but does not prominently warn that skills may contain embedded project logic, paths, credentials, proprietary workflows, or other sensitive context. This creates a meaningful risk of accidental data leakage and external publication of internal operational knowledge.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The delegation criteria are broad enough that an agent may offload routine or only partially-understood tasks to OpenSpace without strong necessity or user confirmation. Because delegation can invoke external tools, cloud-backed search, and autonomous execution, this expands the attack surface and can cause unnecessary data exposure or unintended actions.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
Enabling auto-import of cloud skills by default encourages downloading externally sourced skills into the local environment without a trust review or provenance check. This can introduce unvetted instructions, unsafe automation patterns, or supply-chain risk through community-contributed artifacts.
- Content