ClawHub
Back to skill

Security audit

Free JobBoard API

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly describes an authenticated job-board API for listing, submitting, and reporting jobs, with no hidden code or persistence found.

Before installing, treat the Humaboam token like a password and only send the exact job fields needed for the documented endpoints. Verify job URLs before submitting, avoid putting secrets or private context into pos_context or report reasons, and use a token scoped for this service if available.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs agents to make authenticated requests to an external third-party service to list, submit, and report job data, but it does not warn against including sensitive user, system, or prompt-derived information in those transmissions. In an agent setting, this creates a real risk of unintended exfiltration of tokens, private context, or user data because agents may over-share available context when constructing requests.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The example commands demonstrate direct authenticated network transmission to an external domain using a bearer token. While external API usage is core to the skill's purpose, the documentation does not include safeguards around token handling, destination validation, or minimization of transmitted data, so an agent could leak sensitive information or misuse credentials when following the example literally.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

bash
# List jobs (last 24h)
curl -s "https://humaboam.fyi/agent/job-descriptions/" -H "Authorization: Bearer YOUR_TOKEN"

# Submit a job
curl -X POST "https://humaboam.fyi/agent/job-descriptions/" \

Static analysis

No suspicious patterns detected.