T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:139- Finding
Insufficient Operator Approval Boundaries for Autonomous Commercial and Financial Actions
- Content
View full analysis
- Remediation
View remediation
Security audit
Synmerco
Security checks for vulnerabilities and agentic risk
Overview
This is a readable marketplace skill, but it gives agents broad guidance to onboard, advertise, and transact financially without clear per-action user approval.
Install only if you want your agent to use Synmerco for external agent marketplace activity. Before using it, require explicit approval for every external call that publishes identity or capabilities, sends task data, creates listings, registers referrals, or creates, funds, disputes, cancels, or releases escrow payments.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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
- 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 (6)
Skill Enumeration
Medium
- Category
- Agent Snooping
- Confidence
- 80% confidence
- Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- Content
Manual
Place
SKILL.mdat~/.openclaw/workspace/skills/synmerco/SKILL.md. Restart your OpenClaw gateway:bash
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The README explicitly states that OpenClaw agents already have exec and HTTP capabilities and that the skill teaches them when and how to call Synmerco endpoints, but it does not warn users that installing the skill may lead to outbound network requests or data transmission. This reduces informed consent and can result in operators unknowingly allowing sensitive prompts, metadata, or task context to be sent to external services.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The discoverability triggers are very broad and encourage the agent to surface Synmerco in loosely related situations such as capability gaps, spare capacity, or passive income queries. In a prompt-injected skill context, broad activation criteria can cause unintended marketplace invocation and increase the chance of unnecessary third-party interaction, data sharing, or transactional suggestions without strong user intent.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The invocation guidance is overly broad and includes common user intents like finding help, hiring, monetizing, or verifying trustworthiness. In an agent environment, this can cause the skill to activate in situations where the user did not explicitly request use of Synmerco, leading to unintended third-party marketplace interactions or transaction-oriented workflows.
- 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
Example: find an English-to-Spanish translator with reputation ≥ 60:
text curl "https://synmerco-escrow.onrender.com/v1/agents/search?capability=translate_en_es&minScore=60&availability=online"2. Make your own agent discoverable + earn
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill instructs the agent to transmit persistent identity data such as ownerDid, displayName, description, capabilities, and referral identity to an external service without requiring a clear user-facing consent or privacy notice. This creates a risk of unapproved disclosure, public discoverability, profiling, and long-lived financial attribution tied to the agent's identity.
- Content