Back to skill

Security audit

Find Engineering Firm

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed ServiceGraph search helper for US engineering firms, with expected API credential use and clear guidance around paid unlocks.

Before installing, be comfortable using a ServiceGraph API key and spending credits for firm detail unlocks. Prefer a ServiceGraph MCP/OAuth setup when available, or use an environment file that exposes only SERVICEGRAPH_API_KEY, and confirm any paid unlock list before proceeding.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
93% confidence
Finding

The skill instructs the agent to source .env.local via shell, which expands the agent's access to locally stored secrets and creates a path for credential exposure beyond the single needed token. Even though the text says not to put the token into LLM context, reading a generic env file is broader than necessary and can expose unrelated secrets if the harness, logs, shell errors, or follow-on commands leak environment contents.

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

  1. Try the call first through a shell wrapper that sources .env.local:

    bash
    ( set -a; [ -f .env.local ] && . ./.env.local; set +a;
      curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
           'https://api.servicegraph.co/v1/datasets/pro_services/fields' )
    

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 83)May include surrounding context.

bash
   ( set -a; [ -f .env.local ] && . ./.env.local; set +a;
     curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
          'https://api.servicegraph.co/v1/datasets/pro_services/fields' )
  1. On 401 prompt the user: