ClawHub
Back to skill

Security audit

SyncSo

Security checks for vulnerabilities and agentic risk

Overview

SyncSo is a disclosed NYC event-search integration that uses the user's own account token and relevant outing details to query its external service.

Install only if you are comfortable giving SyncSo an account token and sending relevant outing details, location, preferences, accessibility needs, or budget constraints to its service. Avoid including unrelated sensitive profile information, and remember that calls can spend the user's SyncSo credits or allowance.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
**If it does not**, the tool definitions are at the end of this file.
Add them to your model's tools and POST each call as JSON-RPC to that same
URL, carrying the access token from the section below. The reply is
`result.content[0].text` — compact text, about 120 tokens per result, ready
to hand straight back to the model.

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

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
**If it does not**, the tool definitions are at the end of this file.
Add them to your model's tools and POST each call as JSON-RPC to that same
URL, carrying the access token from the section below. The reply is
`result.content[0].text` — compact text, about 120 tokens per result, ready
to hand straight back to the model.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger guidance is intentionally broad: 'use this whenever someone asks what to do, where to go, what is on.' That overlaps with many routine conversations and can cause the agent to invoke an external third-party service more often than the user explicitly expects, increasing unnecessary data sharing and the chance of tool misuse.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The body text directs the agent to use the tool for broad, ambiguous prompts such as 'what to do' or planning an evening. Because the tool sends user requests and contextual profile details to an external service, overly broad activation expands data exposure beyond what is necessary for many ordinary chats.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill instructs the agent/client to POST user requests to an external endpoint, including free-form request text that may contain sensitive personal context. This creates a real data exfiltration path to a third party, and the skill explicitly encourages including user attributes and preferences that may be privacy-sensitive.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

fetch it again rather than answer from stale guidance.

sh
curl -sS https://rtdb.syncso.com/partner/mcp \
  -H "Authorization: Bearer $SYNCSO_TOKEN" \
  -H "X-SyncSo-Skill: 2.1.0" \
  -H "Content-Type: application/json" \