ClawHub
Back to skill

Security audit

VeilStrat — AI Buyer Intelligence

Security checks for vulnerabilities and agentic risk

Overview

The skill provides company research through a narrowly scoped API client, with disclosed credential use and no hidden actions found.

Public previews need no key. For API access, configure VEILSTRAT_API_KEY through your host's secret settings and consider the service's subscription requirements, quotas and receipt of your research queries. Publisher identity was unavailable in metadata, and authenticated service behavior was not tested.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tainted flow: 'req' from os.environ.get (line 68, credential/environment) → urllib.request.build_opener.open (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/veilstrat.py (reported line 71)May include surrounding context.

python
req = urllib.request.Request(url, data=payload, headers=headers, method=method)
    opener = urllib.request.build_opener(NoRedirect())
    try:
        response = opener.open(req, timeout=TIMEOUT_SECONDS)
    except urllib.error.HTTPError as exc:
        usage = {name: exc.headers[name] for name in USAGE_HEADERS if exc.headers.get(name) is not None}
        try:

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

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.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

md
- **Public research:** Use the host's web search or fetch tools to inspect the directory pages in [references/api.md](references/api.md). No key is needed. Label results as public previews; never describe them as the complete dataset.
- **API research:** Use the bundled Python 3 client. Require `VEILSTRAT_API_KEY` in the execution environment. The account needs Pro with the API Access add-on. Create a key in [Settings → API](https://app.veilstrat.com/), then configure it as a secret in the host. Do not ask the user to paste the key into conversation or place it in a command argument.

The client needs Python 3.9+ with its standard library only. Send API traffic exclusively to `https://app.veilstrat.com/api/v1`. It performs read operations, including a POST-based search, without changing accounts or sending outreach. Queries and company IDs are sent to VeilStrat; successful metered calls use the account's API quotas. The client does not write files, install packages, or send telemetry.