Back to skill

Security audit

FeedOracle Compliance Intelligence

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed compliance-data connector that sends limited, user-requested queries to FeedOracle and does not include local executable code or hidden persistence.

Install only if you are comfortable sending stablecoin symbols or explicit compliance questions to feedoracle.io. Avoid including PII or unrelated conversation context, use audit logging and KYA registration only when you intend the remote service to retain that data, and prefer a pinned installer version instead of an @latest command when available.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
README.md:178
Finding
Unpinned Third-Party Package Execution via npx## Vulnerability Details **File Location**: `README.md:178` **Vulnerability Type**: Insecure dependency installation using a mutable package tag **Risk Level**: Medium ### Vulnerable Code ```bash npx clawhub@latest install feedoracle-compliance ``` ### Technical Analysis The documented installation command instructs `npx` to retrieve and execute the `latest` release of the third-party `clawhub` package. The `latest` tag is mutable, so the code executed by this command can change after this Skill has been reviewed. The project does not include a package lockfile, integrity hash, signature-verification procedure, or local copy of that package through which the executed version can be independently audited. This is a supply-chain weakness rather than evidence that the current package is malicious. Exploitation would require compromise of the package, its publisher account, or its distribution channel, or publication of an unexpectedly unsafe release under the mutable tag. ### Attack Path 1. An attacker compromises the package publisher account, package registry, or release process associated with `clawhub`. 2. The attacker publishes a malicious release and assigns it to the mutable `latest` tag. 3. A user follows the installation instructions and runs the documented `npx` command. 4. `npx` downloads and executes the attacker-controlled package code. 5. The malicious package operates with the permissions of the user who launched the command and can access resources available to that account. ### Impact Assessment Successful exploitation could result in arbitrary code execution under the installing user's privileges. Depending on the user's environment and permissions, the malicious package could read or alter user-accessible files, access environment variables and credentials available to the process, modify local configuration, make network requests, or install additional components. The scope is normally limited to the ...[truncated 125 chars]
Remediation
## Remediation Suggestions - Replace the mutable `@latest` tag with an exact, reviewed package version. - Publish the expected package version and integrity digest alongside the installation instructions. - Where supported, require registry provenance or publisher-signature verification before installation. - Document how users can inspect the package and verify its checksum before execution. - Recommend running installation without elevated privileges and within a restricted or disposable environment. - Establish a controlled update process in which new versions are reviewed before the pinned version is changed.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Content
---
name: feedoracle-compliance
description: "MiCA compliance evidence and stablecoin risk scoring for regulated tokenized markets. 27 MCP tools with ES256K-signed responses. Use when the user explicitly asks about stablecoin compliance, MiCA regulatory status, or needs verifiable evidence for audit workflows."
version: 1.2.2
metadata:
  openclaw:
    requires:
      bins:
        - curl
    emoji: "🛡️"
    homepage: https://feedoracle.io
---

# FeedOracle Compliance Intelligence

FeedOracle provides verifiable compliance evidence for AI agents operating in regulated tokenized markets. Every response is ES256K-signed (J
Confidence
80% confidence
Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Context Leakage

High
Category
Data Exfiltration
Content
Includes: `compliance_preflight`, `mica_status`, `mica_full_pack`, `mica_market_overview`, `peg_deviation`, `peg_history`, `significant_issuer`, `interest_check`, `document_compliance`, `reserve_quality`, `rlusd_integrity`, `evidence_profile`, `evidence_leaderboard`, `evidence_bundle`, `custody_risk`, `market_liquidity`, `macro_risk`, `ai_explain`, `ai_provenance`, `kya_status`, `audit_query`, `audit_verify`, `ping`, `generate_report`

**ai_query — sends question text (user-initiated only):**
This tool sends the user's natural language question to feedoracle.io for routing to the correct evidence API. **Only invoke when the user explicitly asks a compliance question.** Do not send conversation history, PII, or unrelated text.

| Sent | NOT sent |
|------|----------|
Confidence
85% confidence
Finding
Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# MiCA compliance check (no auth needed)
curl -s -X POST https://feedoracle.io/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding
The README instructs users to run `npx clawhub@latest install`, which pulls and executes the latest published package code at install time without pinning a trusted version. If the upstream package is compromised or a malicious update is published, users and agents could execute attacker-controlled code during installation.

Static analysis

No suspicious patterns detected.