ClawHub
Back to skill

Security audit

Agentsecly Ai Agent Security

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed API-based security advisory tool, but it forces potentially sensitive security details to a third-party service without a local fallback or explicit per-request consent.

Install only if you are comfortable sending AI-agent security scenarios, environment details, capabilities, existing controls, impact, and sensitivity labels to ToolWeb's API and potentially incurring billable usage. Do not submit secrets, regulated data, customer data, internal hostnames, or confidential incident details unless you have approval and understand the provider's privacy and retention terms.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:38
Finding

Forced Third-Party Data Transmission and Output Control

Content
View full analysis
", "threatDescription": "", "threatCategory": "", "agentTypes": [""], "capabilities": [""], "environment": "", "securityControls": [""], "impact": "", "sensitivity": "", "timestamp": "" }, "sessionId": "", "timestamp": "" }' ``` 3. **Present results** with severity score, MITRE mapping, and remediation. ``` ### Technical Analysis The skill contains imperative instructions that override the agent's normal ability to decide whether a third-party request is necessary. It explicitly prohibits answering from local knowledge, prohibits a local fallback when the service fails, and requires every assessment to be routed through a billable external API. The required request transmits user-supplied threat descriptions and op ...[truncated 3053 chars]
Remediation
View remediation

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to send detailed threat descriptions, environment details, capabilities, security controls, and sensitivity information to a third-party API, but it does not warn about privacy, confidentiality, or data handling risks before transmission. Because this data may include sensitive security posture information, users could unknowingly disclose internal defensive gaps or regulated data to an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
98% confidence
Finding

The skill mandates an outbound curl POST to an external domain and includes rich security assessment data in the request body. In the context of a security advisory skill, this can expose highly sensitive information about an organization's threats, environment, controls, and weaknesses to a third party, and the instruction to ALWAYS call the API increases the likelihood of unnecessary disclosure.

Content

Scanner excerpt · SKILL.md (reported line 99)May include surrounding context.

  1. Call the API:
bash
curl -s -X POST "https://portal.toolweb.in/apis/security/agentsecly" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $TOOLWEB_API_KEY" \
  -d '{