ClawHub
Back to skill

Security audit

search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward hosted search and content-extraction helper, but users should treat searches and URLs as data sent to a third-party API.

Install only if you are comfortable using SkillBoss/HeyBoss as a third-party processor. Do not submit secrets, proprietary code, internal URLs, private documents, or authenticated links unless that sharing is allowed by your organization.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Context-Inappropriate Capability

Medium
Confidence
85% confidence
Finding
The script submits arbitrary user-provided URLs to an external scraping service, which creates a data egress path and enables third-party retrieval of whatever URLs the caller supplies. In an agent-skill context with no stated trust boundaries, allowlist, or disclosure, this can expose internal URLs, sensitive query strings, or other private targets to an external provider.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script sends the user-supplied query and an authenticated request to a third-party API without any disclosure, confirmation, or warning to the user at runtime. In a skill context, users may reasonably assume local processing, so silently transmitting potentially sensitive code-search terms or internal identifiers externally creates a real privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script makes an authenticated request to a third-party endpoint using a bearer token while transmitting user-supplied URLs, but provides almost no user-facing disclosure beyond a brief comment. This is dangerous because users may not realize their input is being forwarded to an external service, potentially leaking sensitive destinations or embedded secrets in URLs.

External Transmission

Medium
Category
Data Exfiltration
Content
prefer: "balanced"
    }')

curl -s -X POST 'https://api.heybossai.com/v1/pilot' \
    -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "$PAYLOAD"
Confidence
89% confidence
Finding
This command performs an authenticated POST to an external service and includes the user-controlled query in the request body. Even though HTTPS is used, the security issue is the external exfiltration surface itself: sensitive search terms, proprietary code references, or internal documentation identifiers may be disclosed to a third party without minimization or validation.

External Transmission

Medium
Category
Data Exfiltration
Content
prefer: "balanced"
    }')

curl -s -X POST 'https://api.heybossai.com/v1/pilot' \
    -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "$PAYLOAD"
Confidence
89% confidence
Finding
This command performs an authenticated POST to an external service and includes the user-controlled query in the request body. Even though HTTPS is used, the security issue is the external exfiltration surface itself: sensitive search terms, proprietary code references, or internal documentation identifiers may be disclosed to a third party without minimization or validation.

Static analysis

No suspicious patterns detected.