ClawHub
Back to skill

Security audit

CISO Daily Security Pulse

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for a CISO security assessment API, but it can send sensitive organization security posture data and user/session identifiers to an external service without enough scoping or data-handling disclosure.

Install only if you are comfortable sending aggregated security metrics to ToolWeb.in. Avoid secrets, hostnames, asset identifiers, incident details, customer data, or personally identifying user IDs unless your organization has approved that data sharing and retention arrangement.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly solicits detailed security posture data such as vulnerability counts, critical findings, compliance gaps, incident activity, audit dates, and MFA adoption, but provides no warning that this telemetry may be sensitive and will be transmitted to a third-party service. In a CISO-focused tool, this omission is more dangerous because operators may submit organization-level security indicators that could aid targeting, reconnaissance, or vendor-side data exposure if mishandled.

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 139)May include surrounding context.

md
## References

- **Kong Route:** https://api.toolweb.in/tools/ciso-daily-security-pulse
- **API Docs:** https://api.toolweb.in:8203/docs

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is overly broad for a security-sensitive assessment tool and does not define clear invocation boundaries, eligible use cases, or excluded scenarios. This can cause over-invocation on sensitive enterprise data and increase the chance that users or orchestrators send inappropriate or excessive security telemetry to the endpoint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The API accepts arbitrary assessmentData along with sessionId, userId, and timestamp fields, but the specification provides no warning that these fields may contain sensitive operational or personal data. In a CISO-focused security context, this makes accidental transmission of internal security posture details, identifiers, and correlated activity metadata more likely.

Content

No source excerpt is available for this finding.