Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Trading Decision Pro
v1.0.0AI-powered trading decision assistant by Automaton. Market sentiment analysis, risk assessment, real-time trade recommendations.
⭐ 0· 44·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The code and README implement a trading decision assistant as claimed. However SKILL.md and index.js reference features (knowledge injection, session snapshots, cross-review endpoints, tools registry) that are not present in the package manifest. index.js optionally reads process.env.TRADING_DECISION_API_KEY but the skill declares no required env vars — a minor mismatch that should be documented by the author.
Instruction Scope
SKILL.md claims the agent will "automatically search related experience (tasks/KNOWLEDGE.md)" and use files like tasks/SESSION-SNAPSHOT.md and /cross-review, which would require reading local files or calling internal endpoints. Those files/endpoints are not in the bundle. The presence of these instructions gives the agent latitude to access local files if implemented; that scope creep should be justified and the referenced files included or removed.
Install Mechanism
No install/spec that downloads external archives is present. package.json has no dependencies. This is low install risk (no external downloads).
Credentials
The package does not declare required environment variables, but index.js reads process.env.TRADING_DECISION_API_KEY as an optional API key; SKILL.md examples show passing an apiKey. This undocumented env usage should be declared. No other credentials or unrelated env vars are requested.
Persistence & Privilege
Skill settings show no always:true and no special OS/install privileges. The skill does not request to modify other skills or system-wide agent config.
Scan Findings in Context
[ENV_VAR_USAGE:process.env.TRADING_DECISION_API_KEY] unexpected: index.js reads TRADING_DECISION_API_KEY via process.env but requires.env is empty. Using an API key is reasonable for a trading service, but the env var is undocumented in the skill metadata.
What to consider before installing
This skill's code implements a trading assistant and contains no obvious network-download/install steps, but several inconsistencies are concerning: SKILL.md promises automatic "knowledge injection" (searching local files like tasks/KNOWLEDGE.md), cross-review endpoints, and session snapshot files that are not included; index.js optionally reads TRADING_DECISION_API_KEY even though no env is declared; the SKILL.md contains external payment/contact instructions (WeChat/Telegram) which are outside the registry flow.
Before installing or providing any credentials:
- Ask the maintainer to explain and include the referenced files (tasks/KNOWLEDGE.md, SESSION-SNAPSHOT.md, cross-review tooling) or remove those claims.
- Request that the skill metadata explicitly declare any environment variables (e.g., TRADING_DECISION_API_KEY) and document what the key is used for and where network calls go.
- Inspect the remaining parts of index.js (the provided index.js was truncated) for any network calls, hidden endpoints, or data exfiltration logic. Run the bundled tests locally in a sandboxed environment to see behavior.
- Do not provide secrets (API keys, exchange credentials, AWS keys) to the skill until provenance (author/repo) is verified and the env requirements are explicit.
- Be cautious about following payment/contact instructions embedded in SKILL.md; prefer official support channels (registry/maintainer contact) rather than ad-hoc WeChat/Telegram payment flows.
These issues could be innocent sloppy packaging/documentation, but they create risk — treat the package as untrusted until the maintainer resolves the inconsistencies and proves the code's provenance.index.js:18
Environment variable access combined with network send.
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk97d853z7tcgnee0x23hcrrh4s83tn8h
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧠 Clawdis
