T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:88- Finding
Recommended Upload Set Includes Sensitive Agent Configuration and User Context
- Content
View full analysis
- Remediation
View remediation
Security audit
clawgo-upload
Security checks for vulnerabilities and agentic risk
Overview
The skill does what it claims, but it needs review because it encourages uploading sensitive workspace files and whole folders to an external sharing service with limited safeguards.
Install only if you are comfortable with selected files being zipped and uploaded to clawgo.me. Before using it, manually choose the files, avoid persona, policy, user-profile, .env, credential, key, token, cookie, backup, and source-control files, and treat the returned clone link and key as sensitive until the service's retention and access controls are clear.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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
Findings (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:36- Finding
Unrestricted Recursive Archiving Can Upload Secrets and Hidden Files
- 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
- 97% confidence
- Finding
The skill directs local files to be uploaded to a third-party service without an explicit warning that this transfers data off-device and may expose private or sensitive content. In context, the skill is designed for sharing or backing up workspace content, so missing consent and privacy language materially raises the risk of unintentional exfiltration.
- Content
Ssd 3
High
- Category
- Not specified by scanner
- Confidence
- 99% confidence
- Finding
The skill explicitly recommends uploading OpenClaw workspace files such as SOUL.md, AGENTS.md, TOOLS.md, IDENTITY.md, and USER.md, which can contain identity data, behavioral rules, tool access hints, and user profile/session context. Sending these files to a third-party share service can leak sensitive system prompts, security controls, operational details, and personal context, enabling prompt injection, policy circumvention, privacy breaches, or downstream compromise.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger list includes broad natural-language phrases such as 'share my workspace' and 'zip and upload' that can match common user requests and cause the skill to activate in situations the user may not intend. Because this skill performs packaging and remote upload of local files, accidental activation increases the chance of unintended data disclosure.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The trigger phrases are broad enough to match common user intents such as sharing a workspace or uploading files, but the description does not clearly constrain what file types, paths, or destinations are in scope. In a skill that zips and uploads local content to an external service, this can cause unintended activation and exfiltration of sensitive local files if the agent misinterprets a general request as consent to upload.
- Content