Back to skill

Security audit

didit-fraud-networks

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because a payout-screening workflow may create a production transaction despite being described as read-only, and the scan inspected only half of its components.

Consider the reported production transaction behavior and missing tool-scope declaration before installing. Skillspector coverage was partial (50%): one component was fully inspected and one partially inspected, with a static analysis limit, so the evidence is incomplete.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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: 'get_api_key()' from os.environ.get (line 52, credential/environment) → requests.get (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/list_networks.py (reported line 63)May include surrounding context.

python
def get(url: str, params: dict = None) -> dict:
    r = requests.get(url, headers={"x-api-key": get_api_key()}, params=params, timeout=60)
    if r.status_code != 200:
        print(f"Error {r.status_code}: {r.text}", file=sys.stderr)
        sys.exit(1)

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.

The payout-screening workflow creates a transaction without warning that it changes production data.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The payout-screening workflow starts with POST /v3/transactions/, a state-changing operation, despite describing the skill as read-only. An agent following this workflow for a lookup-only request could create an unintended production transaction record, potentially affecting downstream processing or fraud-network data.

Content

No source excerpt is available for this finding.