Back to skill

Security audit

Attio Integration

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because its reported capabilities include workspace user and group administration and an API credits request beyond its stated CRM purpose.

Consider the suspicious verdict and the reported mismatch with the skill's CRM purpose before installing. In particular, review whether you need its workspace user and group administration and whether the API credits request is appropriate. The scan reports complete file coverage, but its findings still warrant caution.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code only queries the credits endpoint and performs no Attio CRM operations. Credit information is outside the declared resource scope, and the chunk contains no CRM workflow for which this request would serve as a supporting implementation detail.

Content

No source excerpt is available for this finding.

SCIM user and group administration exceeds the manifest's stated CRM resource-management scope.

High
Category
Excessive Agency
Confidence
96% confidence
Finding

The manifest at L0003 describes managing CRM records, lists, notes, tasks, and meetings, but L1923–L2030 expose operations to create, modify, and delete workspace users and groups through SCIM. Identity provisioning and deprovisioning can affect workspace access and are not necessary implementation details of managing those CRM resources; the broader API-surface disclosure at L0026 does not align the manifest description with these capabilities.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

Verify the install (do this first)

bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

Base URL

text
https://api.superagnt.com/v1/connections/attio

Available Endpoints

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 2144)May include surrounding context.

Example

bash
curl -X GET 'https://api.superagnt.com/v1/connections/attio/v2/objects&; \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'