ClawHub
Back to skill

Security audit

Iseclaw Intel

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed crypto market-intelligence helper that points users to external market-data and paid research services, with notable financial-risk caveats but no hidden execution, persistence, or local data access.

Install only if you are comfortable with a crypto-focused skill that relies on third-party web services and paid ACP research. Treat all token signals, price targets, and market sentiment as unverified information, not financial advice, and avoid sending sensitive personal or account data in requests.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (7)

External Transmission

Medium
Category
Data Exfiltration
Confidence
79% confidence
Finding

The skill instructs users or agents to send requests to an external domain, which creates a data transmission boundary outside the host platform's control. Even if the endpoint appears to be a normal API, requests may expose user metadata, usage patterns, IP addresses, and any future query contents to a third party, which is risky in a finance-related skill.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

�� Live Market Pulse

text
GET https://api.zerovantclaw.xyz/market-pulse

Example response:

json

External Transmission

Medium
Category
Data Exfiltration
Confidence
79% confidence
Finding

This endpoint similarly causes outbound requests to a third-party API, extending trust to infrastructure outside the platform. In the context of real-time token pricing and sentiment, tampered or misleading data could influence user financial decisions in addition to the ordinary privacy risks of external transmission.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

�� Indo Watchlist (Real-time prices)

text
GET https://api.zerovantclaw.xyz/indo-watchlist

Example response:

json

External Transmission

Medium
Category
Data Exfiltration
Confidence
78% confidence
Finding

The TGE calendar endpoint introduces the same external transmission risk and, because it concerns trending and upcoming token events, it can materially shape speculative behavior if the source is inaccurate or manipulated. Users may treat the feed as trusted intelligence without understanding that the data comes from an external, uncontrolled service.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

�� TGE Calendar (Trending + Upcoming)

text
GET https://api.zerovantclaw.xyz/tge-calendar

Returns trending coins + curated upcoming TGE events from Indonesian Web3 community.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill provides explicit trading-oriented outputs such as entry zones, targets, stop losses, and confidence scores without any disclaimer that the content is informational only and not financial advice. In a crypto context, users may reasonably act on these recommendations, increasing the risk of financial harm and creating an unsafe impression of authoritative investment guidance.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
81% confidence
Finding

The quick-usage examples operationalize the external API calls, making outbound transmission more likely in practice rather than merely descriptive. This increases the chance that users or integrated agents will contact the third-party domain without considering privacy, provenance, or reliability implications.

Content

Scanner excerpt · SKILL.md (reported line 120)May include surrounding context.

Quick Usage

text
# Get market pulse
fetch https://api.zerovantclaw.xyz/market-pulse

# Get token watchlist
fetch https://api.zerovantclaw.xyz/indo-watchlist

External Transmission

Medium
Category
Data Exfiltration
Confidence
81% confidence
Finding

This second quick-usage example likewise directs traffic to the external API and normalizes reliance on a third-party service for market data. In a crypto trading context, any compromised, spoofed, or low-integrity external feed can mislead users into poor decisions while also collecting access metadata.

Content

Scanner excerpt · SKILL.md (reported line 123)May include surrounding context.

md
fetch https://api.zerovantclaw.xyz/market-pulse

# Get token watchlist
fetch https://api.zerovantclaw.xyz/indo-watchlist

# Hire for deep research (ACP)
acp hire iseclaw token_signal --input '{"token": "SOL"}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The description repeatedly frames the skill as being for Indonesian Web3 intelligence, which may constitute a locale-specific constraint. Because the file does not explicitly offer an opt-in choice or clarify that the regional focus is an intentional, documented specialization for that market, it can be read as a language/locale restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.