Back to skill

Security audit

Find Management Consultant

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned for finding consulting firms, but its fallback authentication instructions unsafe execute a local .env file as shell code.

Review before installing. Prefer the MCP flow or an already-exported, scoped SERVICEGRAPH_API_KEY, and avoid running the documented .env.local sourcing command unless you fully trust that file. Confirm paid unlocks before use because full enrichment spends ServiceGraph credits.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:70
Finding

Arbitrary Command Execution Through Unsafe Dot-Sourcing of .env.local

Content
View full analysis
Remediation
View remediation
&2 exit 1 fi curl -sS \ -H "Authorization: Bearer ${SERVICEGRAPH_API_KEY}" \ 'https://api.servicegraph.co/v1/datasets/pro_services/fields' ``` This approach uses only an existing environment variable and does not execute a project-local configuration file. ]]>
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
90% confidence
Finding

The skill explicitly directs the agent to source .env.local and use SERVICEGRAPH_API_KEY in a shell command. Although it says not to place the token in LLM context, instructing an agent to read local environment files for credentials is a credential-access pattern that can be abused if the skill is invoked in an unsafe context, expanded later, or combined with prompt injection to access other secrets.

Content

Scanner excerpt · SKILL.md (reported line 70)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
95% confidence
Finding

The skill instructs the agent to send authenticated requests to an external third-party API using a bearer token sourced from the local environment. Even though the destination appears expected for the skill’s purpose, this still creates a real data-exfiltration boundary because the agent is authorized to transmit secrets and potentially user-derived query data off-platform to an external service.

Content

Scanner excerpt · SKILL.md (reported line 72)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: