Back to skill

Security audit

search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward wrapper around a third-party web search and content extraction API, with remote data sharing disclosed at a basic level.

Install only if you are comfortable sending search queries, requested URLs, and your SkillBoss API token to the HeyBossAI/SkillBoss API. Do not use it with private internal URLs, credential-bearing links, or sensitive queries unless that third-party processing is acceptable for your environment.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The description claims both web search and content extraction, but the supplied code only performs content extraction for user-provided URLs by POSTing a scraping request to the API. There is no logic for search queries, discovery of web results, or finding documentation/research/company info beyond scraping explicitly supplied URLs. The API key requirement matches the description, but the primary declared capability is broader than the implemented behavior.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 · scripts/code.sh (reported line 34)May include surrounding context.

sh
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"

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 · scripts/search.sh (reported line 48)May include surrounding context.

sh
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"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/code.sh (reported line 34)May include surrounding context.

sh
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"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/search.sh (reported line 48)May include surrounding context.

sh
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"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script sends the user-provided query in the JSON payload to an external HTTPS endpoint, but there is no runtime notice, confirmation, or user-facing output explaining that the query content will be transmitted off-system. The only related text is an internal comment, which does not reliably disclose this behavior to users invoking the script.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The hardcoded external endpoint confirms that all extracted content requests are routed to a third-party service rather than processed locally. This is not inherently malicious, but it is security-relevant because it expands the trust boundary and may leak operational metadata or sensitive URL inputs to the provider.

Content

Scanner excerpt · scripts/content.sh (reported line 25)May include surrounding context.

sh
}
        }')

    curl -s -X POST 'https://api.heybossai.com/v1/pilot' \
        -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
        -H 'Content-Type: application/json' \
        -d "$PAYLOAD"

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The hardcoded external endpoint confirms that all extracted content requests are routed to a third-party service rather than processed locally. This is not inherently malicious, but it is security-relevant because it expands the trust boundary and may leak operational metadata or sensitive URL inputs to the provider.

Content

Scanner excerpt · scripts/content.sh (reported line 25)May include surrounding context.

sh
}
        }')

    curl -s -X POST 'https://api.heybossai.com/v1/pilot' \
        -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
        -H 'Content-Type: application/json' \
        -d "$PAYLOAD"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script transmits user-supplied URLs to a third-party API service, which is a real data-flow/security concern because URLs can contain sensitive query parameters, internal hostnames, or links to private resources. While this appears consistent with the skill’s stated purpose, the disclosure is minimal and users may not realize their inputs are being sent off-box to an external provider.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This shell script sends the supplied search query to an external service using curl, which is a network operation that transmits user-provided data. Although the file has an internal comment and an API-key setup message, it does not provide a runtime warning, confirmation, or other user-facing disclosure that the query content will be sent to a third-party endpoint.

Content

No source excerpt is available for this finding.