ClawHub
Back to skill

Security audit

customer-promise-tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly teaches users to send customer promise records to BlueColumn, which is purpose-aligned but requires privacy care.

Install only if BlueColumn is approved for your customer and business data. Avoid sending secrets, regulated data, unnecessary personal details, or internal-only links; use minimized summaries or opaque record IDs where possible.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description explicitly says it extracts commitments from customer calls and messages and requires sending that content to BlueColumn, but it does not provide a clear user-facing warning that customer communications, employee names, and source links will be transmitted to a third-party service. This creates a real privacy and compliance risk because users may supply sensitive business or personal data without informed consent or data-minimization safeguards.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The example payload includes identifiable employee and customer names, a promise involving security documentation, and a direct CRM evidence URL, all of which are sent to an external API. Because the skill provides no warning or constraints around sensitive data handling, it normalizes transmitting potentially confidential customer records and internal links to a third party.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This command sends structured customer-relationship data to an external endpoint, including names, commitment details, dates, and a CRM evidence link. The transmission itself is expected functionality, but in this context it is security-relevant because it exports potentially sensitive business data to a third party without any embedded guardrails, minimization guidance, or consent/compliance notice.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

After a call or thread, store each commitment with who, what, when, and the source.

bash
curl -X POST https://api.bluecolumn.ai/remember \
  -H "Authorization: Bearer $BLUECOLUMN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This command sends structured customer-relationship data to an external endpoint, including names, commitment details, dates, and a CRM evidence link. The transmission itself is expected functionality, but in this context it is security-relevant because it exports potentially sensitive business data to a third party without any embedded guardrails, minimization guidance, or consent/compliance notice.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

After a call or thread, store each commitment with who, what, when, and the source.

bash
curl -X POST https://api.bluecolumn.ai/remember \
  -H "Authorization: Bearer $BLUECOLUMN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

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 33)May include surrounding context.

Close the loop when it ships.

bash
curl -X POST https://api.bluecolumn.ai/note \
  -H "Authorization: Bearer $BLUECOLUMN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "DONE: Acme SOC2 report sent 09-29 14:05 by Sarah. Promise fulfilled.", "tags": ["promise", "fulfilled"]}'

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 44)May include surrounding context.

Close the loop when it ships.

bash
curl -X POST https://api.bluecolumn.ai/note \
  -H "Authorization: Bearer $BLUECOLUMN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "DONE: Acme SOC2 report sent 09-29 14:05 by Sarah. Promise fulfilled.", "tags": ["promise", "fulfilled"]}'

Static analysis

No suspicious patterns detected.