ClawHub
Back to skill

Security audit

Attio Integration

Security checks for vulnerabilities and agentic risk

Overview

The skill is a documented Attio integration, but it exposes broad administrative Attio powers beyond routine CRM work, including SCIM user/group management, files, transcripts, webhooks, and deletions.

Review this carefully before installing. Use it only if you intend to let an agent operate a broad Attio connection, not just basic CRM records. Prefer a least-privilege Attio/Superagnt connection where possible, and require explicit confirmation for SCIM user/group changes, webhook changes, file access, transcript access, and any create/update/delete operation.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Context-Inappropriate Capability

High
Confidence
97% confidence
Finding
Including SCIM user and group provisioning in a skill framed as CRM management materially expands its authority into identity and access administration. If an agent is allowed to use this skill for routine CRM tasks, those same credentials could create, modify, or delete users and groups, leading to privilege changes, account lifecycle abuse, or organizational disruption.

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The manifest description presents the skill as simple CRM record/list/task/meeting management, but the documented capability set also includes SCIM identity provisioning, webhooks, files, threads/comments, and call recordings. This scope understatement is dangerous because agents or reviewers may grant or invoke the skill under a narrower trust assumption than its actual authority, increasing the chance of unintended access to identity, file, and communication data or destructive administrative actions.

External Transmission

Medium
Category
Data Exfiltration
Content
## Verify the install (do this first)

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
## Verify the install (do this first)

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
## Verify the install (do this first)

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.