ClawHub
Back to skill

Security audit

B2B Contact Enrichment

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed FinalScout integration for finding professional contact emails, with expected privacy considerations around sending contact data to an external API.

Install only if you intend to send the provided names, domains, LinkedIn URLs, article URLs, and optional metadata to FinalScout. Be careful with bulk lead lists, user-provided webhook URLs, personal-email fallback, and CSV export links because exported results may be publicly accessible to anyone with the link until expiry.

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 (11)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README describes transmitting personal/contact data to FinalScout and optionally to arbitrary webhooks without warning users that their input will leave the local environment. Because this skill handles professional identities, LinkedIn URLs, article URLs, metadata, and potentially bulk contact lists, missing disclosure and consent guidance can lead to privacy, compliance, and accidental exfiltration issues.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction to 'Just ask in natural language' makes the skill’s activation and scope overly broad, increasing the chance it will be invoked on loosely related prompts and process sensitive data unintentionally. In a skill that sends contact details to an external enrichment API and may trigger webhooks, ambiguous invocation boundaries materially raise the risk of unintended external data disclosure or unexpected actions.

Content

No source excerpt is available for this finding.

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 · SKILL.md (reported line 86)May include surrounding context.

One blocking call; the server holds the connection until the task finishes or timeout (seconds, 30–600, default 80) is reached.

bash
curl -s -m 130 -w "\nHTTP %{http_code}" \
  "https://api-waterfall.finalscout.com/find/professional/single?timeout=120" \
  -H "Authorization: $FINALSCOUT_API_KEY" \
  -H "Content-Type: application/json" \

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 112)May include surrounding context.

Submit (same bodies and optional fields as waterfall):

bash
curl -s -X POST https://api.finalscout.com/v1/find/professional/single \
  -H "Authorization: $FINALSCOUT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"person":{"full_name":"<name>","domain":"<domain>"}}'

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 122)May include surrounding context.

Submit (same bodies and optional fields as waterfall):

bash
curl -s -X POST https://api.finalscout.com/v1/find/professional/single \
  -H "Authorization: $FINALSCOUT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"person":{"full_name":"<name>","domain":"<domain>"}}'

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 137)May include surrounding context.

Submit (same bodies and optional fields as waterfall):

bash
curl -s -X POST https://api.finalscout.com/v1/find/professional/single \
  -H "Authorization: $FINALSCOUT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"person":{"full_name":"<name>","domain":"<domain>"}}'

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 164)May include surrounding context.

Submit (same bodies and optional fields as waterfall):

bash
curl -s -X POST https://api.finalscout.com/v1/find/professional/single \
  -H "Authorization: $FINALSCOUT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"person":{"full_name":"<name>","domain":"<domain>"}}'

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 173)May include surrounding context.

Submit (same bodies and optional fields as waterfall):

bash
curl -s -X POST https://api.finalscout.com/v1/find/professional/single \
  -H "Authorization: $FINALSCOUT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"person":{"full_name":"<name>","domain":"<domain>"}}'

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 193)May include surrounding context.

Submit (same bodies and optional fields as waterfall):

bash
curl -s -X POST https://api.finalscout.com/v1/find/professional/single \
  -H "Authorization: $FINALSCOUT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"person":{"full_name":"<name>","domain":"<domain>"}}'

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 204)May include surrounding context.

Submit (same bodies and optional fields as waterfall):

bash
curl -s -X POST https://api.finalscout.com/v1/find/professional/single \
  -H "Authorization: $FINALSCOUT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"person":{"full_name":"<name>","domain":"<domain>"}}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly instructs users to use a public CSV download link for exported contact data and only adds the warning after the export flow is described. Because the skill handles personal/professional contact data, delayed disclosure increases the chance users will expose sensitive lead lists or enrichment results to anyone who obtains the URL.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.