ClawHub
Back to skill

Security audit

SaffronAI ETF Data

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward public ETF data fetcher with disclosed network access and no evidence of hidden persistence, credential access, or destructive behavior.

Install only if you are comfortable with the skill making network reads to SaffronAI's public ETF endpoint and running its bundled Python helper. No credential access or local data mutation was found, but adding explicit tool restrictions and documenting the curl dependency would improve transparency.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill invokes shell commands (python3 ...) but does not declare any tool restrictions such as permissions or allowed-tools. Even though the documented use appears limited to fetching public ETF data, missing scope allows a broader execution surface than necessary and weakens enforcement of least privilege.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill's stated purpose is to fetch ETF tracker data from SaffronAI and return it as JSON or filtered rows. While network access is expected for that purpose, spawning an external command-line tool is an additional capability not justified by the manifest description, which presents the skill as a simple data fetcher rather than one that executes system binaries.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/saffronai_etf.py (reported line 30)May include surrounding context.

python
# Use curl for resilience and to align with OpenClaw skill expectations.
    # -sS: silent but show errors
    # --fail: non-2xx => exit non-zero
    res = subprocess.run(
        ["curl", "-sS", "--fail", URL],
        check=True,
        stdout=subprocess.PIPE,

Static analysis

No suspicious patterns detected.