trade-signal
3 findings (1 high, 1 medium, 1 low), mainly social engineering, data exfiltration. Most recent scan 2026-02-07.
This skill presents MEDIUM-HIGH security risk primarily due to unvalidated external API data transmission and misleading capability claims. The skill is essentially a wrapper around an external financial search API (terminal-x.ai) but markets itself as providing 'executable trade signals' and 'real-time recommendations' which overstates its actual functionality. The main security concern is that user queries containing potentially sensitive financial information are sent to an external third-party API without transparency about data handling, authentication, or privacy practices. Additionally, the skill references non-existent Python files and lacks important metadata. While there are no direct prompt injection attempts or malicious code execution patterns, the combination of external data transmission, misleading marketing, and incomplete implementation creates meaningful security and trust concerns for users making financial decisions.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco rates this HIGH and SkillSpector found nothing. Check the false-positive register; signature matches on documentation are the usual cause. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Real-time trade signals with executable Buy/Sell/Hold recommendations for stocks. Use when asked about trading decisions, stock analysis, technicals, buy/sell calls, earnings plays, price targets, analyst ratings, entry/exit points, portfolio rebalancing, or any investment decision requiring actionable intelligence. Supports US + Global markets, Asia emerging markets, individual stocks, ETFs, and options strategies.
- Package
- 2 files, 10 KB
- SKILL.md
- 1443 words, 12+ sections
- Code
- Shell (1)
- Version
- 1.0.0
- Homepage
- https://terminal-x.ai
SKILL.md covers: Trade Signal · Quick Start · Get financial analysis · Company comparison · Analyst sentiment · Features · 📊 Research Capabilities · 📈 Market Coverage · 🔬 Data Sources · Usage · Using the Script · Earnings query
Findings
HIGH Unvalidated External API Data Exfiltration Risk Data Exfiltrationllm
The skill sends user queries directly to an external API (https://terminal-x.ai/api) without any validation, authentication mechanism visibility, or data handling transparency. User queries may contain sensitive information about investment positions, portfolio details, or trading strategies that are transmitted to a third-party service. There is no disclosure about data retention, logging, or privacy practices of the external API.
scripts/search.sh:13
ENCODED=$(python3 -c "import urllib.parse; print(urllib.parse.quote('''$QUERY'''))")\ncurl -sL "https://terminal-x.ai/api/lite-search?query=${ENCODED}"MEDIUM Misleading Scope and Capability Claims Social Engineeringllm
The skill description claims to provide 'executable Buy/Sell/Hold recommendations' and 'real-time trade signals' but the actual implementation only performs web searches against an external API. The skill cannot execute trades, provide real-time data (it's a search API), or generate independent trade signals. The description uses aggressive marketing language ('institution-grade trade thesis', 'actionable intelligence') that overstates the capability of a simple API wrapper. This could mislead users into making financial decisions based on misunderstood capabilities.
SKILL.md
Description claims: 'Real-time trade signals with executable Buy/Sell/Hold recommendations' and 'institution-grade trade thesis'\nActual implementation: curl request to search API endpoint with no signal generation, execution capability, or real-time data processingLOW Insufficient Financial Disclaimer Social Engineeringllm
The skill provides financial market information and analysis but lacks adequate disclaimers about the nature of the information, investment risks, or regulatory compliance. Given the sensitive nature of financial advice and potential for user harm from misinterpreted data, stronger disclaimers are needed.
SKILL.md
Skill provides 'Buy/Sell/Hold recommendations' and 'price targets' without disclaimers about: not being financial advice, past performance, risk of loss, or regulatory statusWhat is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 10 KB |
scripts/search.sh | script | 345 B |
External hosts referenced
terminal-x.ai
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/trade-signal
- Raw scan result: trade-singal-scan.json
- Badge for your README:
- Request a re-scan