ClawHub
Back to skill

Security audit

Instantly AI Integration

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Instantly/Superagnt integration, but it exposes broad account-admin, billing, purchasing, API-key, and workspace-owner controls beyond ordinary outreach workflows.

Review this before installing if you only need outreach automation. Use it only with an account/key whose permissions you are comfortable exposing to campaign, lead, email, billing, API-key, procurement, and workspace-admin actions, and require explicit confirmation before sends, deletes, purchases, key changes, billing changes, or workspace membership/ownership changes.

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 (7)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest presents the skill as a narrowly scoped outreach integration, but the documented surface includes privileged administrative functions such as billing, API-key management, workspace administration, and purchasing. This creates a capability/scope mismatch that can cause an agent or user to authorize far broader actions than expected, enabling unintended administrative changes or financial actions.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

Account procurement and billing-adjacent operations are outside the normal expectations of a cold-email outreach skill, yet they are available through the same integration. If an agent is induced to use these endpoints, it could trigger purchases, charges, or provisioning actions on the user's connected account without the narrow context implied by the skill's name and purpose.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

API key lifecycle management allows creation and deletion of credentials that can extend or disrupt access beyond routine outreach tasks. In a skill framed as campaign management, exposing these endpoints increases the risk of secret sprawl, unauthorized persistence, or denial of service through key rotation or deletion.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

Workspace membership and ownership administration are high-privilege controls unrelated to routine outreach execution. Their presence in this skill could let an agent add/remove members, alter roles, or transfer ownership if prompted or manipulated, potentially resulting in account takeover or loss of administrative control.

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 85)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 95)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 5393)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'

Static analysis

No suspicious patterns detected.