ClawHub
Back to skill

Security audit

ai-csuite

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent local decision-support workflow with an optional, disclosed external judgment mode that users should enable only when they are comfortable sending business context to TypeSafe.

Install for local strategic-decision drafting if you are comfortable providing company context to the skill. Keep company.local.yaml and generated logs out of public repos, and do not use --jev unless you intentionally want the listed business context sent to TypeSafe with your TYPESAFE_API_KEY.

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
  • 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
Findings (7)

Tainted flow: 'request' from os.environ.get (line 56, credential/environment) → urllib.request.urlopen (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/jev.py (reported line 63)May include surrounding context.

python
method="POST",
    )
    try:
        with urllib.request.urlopen(request, timeout=TIMEOUT) as response:
            body = json.loads(response.read().decode("utf-8"))
    except Exception as exc:  # noqa: BLE001 - any failure must degrade, not propagate
        # urllib raises across several unrelated trees here: URLError/HTTPError,

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 199)May include surrounding context.

md
- OpenSkills-compatible runners that support `SKILL.md`

Lp1

High
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The code includes outbound network capability that is not covered by declared permissions. Even though the endpoint is hardcoded and the feature is optional, missing permission declarations create a real policy and containment gap because users may run the skill without realizing it can send internal business context to an external service.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The code includes outbound network capability that is not covered by declared permissions. Even though the endpoint is hardcoded and the feature is optional, missing permission declarations create a real policy and containment gap because users may run the skill without realizing it can send internal business context to an external service.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation text says to use the skill whenever the user needs a strategic decision across a very wide set of business topics, but it does not define boundaries for when this skill should be preferred over other planning or advisory skills. Because SKILL.md is a markdown file, this falls under vague trigger review and could cause unintended invocation for ordinary business discussions.

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 · scripts/jev.py (reported line 15)May include surrounding context.

python
import urllib.error
import urllib.request

ENDPOINT = "https://api.typesafe.ai/v1/systemone"
MODEL = "jev-latest"
TIMEOUT = 20

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README explicitly tells users to copy and populate a local company config with real business values, but it does not warn that these fields may contain sensitive internal data such as revenue, runway, team size, and strategic constraints. In a skill designed to generate AI-driven strategic debate artifacts, that omission increases the chance of accidental exposure through commits, logs, or shared outputs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.