Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Crypto Cog
v1.0.10The market never sleeps, and neither does your analysis. #1 on DeepResearch Bench (Apr 2026) applied to crypto — token deep-dives, on-chain metrics, DeFi pro...
⭐ 7· 2.2k·5 current·5 all-time
byCellCog@nitishgargiitd
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill claims deep crypto research which reasonably requires an SDK or external data sources (on-chain APIs, social metrics, etc.). The SKILL.md lists a dependency 'cellcog' which fits this purpose, but the skill does not declare how that dependency is installed or authenticated—an inconsistency between claimed capability and requested/declared requirements.
Instruction Scope
Runtime instructions direct the agent to use the CellCog client to fetch and synthesize on-chain metrics, social sentiment, contract audits, and generate reports (HTML/PDF/XLSX). The instructions do not explicitly tell the agent to read local sensitive files or env vars, but they leave unspecified where on-chain and off-chain data is pulled from and how credentials/session keys are provided. The skill also references 'read the cellcog skill for the full SDK reference', which implies cross-skill dependencies that are not included here.
Install Mechanism
No install spec is provided (instruction-only), which is low-risk in itself. However, the frontmatter dependency 'cellcog' suggests a runtime package is required; the skill gives no guidance on installing that package or which package repository/version to trust. That omission is an operational/information-risk gap rather than an explicit malicious install.
Credentials
No environment variables, API keys, or config paths are declared, yet the examples use a CellCog client and a notify_session_key. Real SDK usage typically requires authentication (API key, token) and network access. The absence of declared credentials or instructions for securely supplying them is a proportionality/information mismatch that could lead users to supply secrets ad hoc or the agent to rely on undocumented credentials.
Persistence & Privilege
The skill does not request 'always: true' and leaves autonomous invocation enabled (the platform default). There is no evidence the skill tries to modify other skills or system-wide settings. No persistence or elevated privilege is requested in the metadata.
What to consider before installing
This skill appears to be a wrapper around a CellCog research SDK and could be legitimate, but it is missing critical operational details: (1) Ask the publisher which package/release to install for the 'cellcog' dependency and whether it's available on PyPI/NPM/GitHub. (2) Confirm how authentication is handled—what API key or token is required, where to store it securely, and whether the skill will ever ask for or handle private keys (never share wallet private keys). (3) Clarify which external data sources are queried (node providers, indexers, social APIs) and whether any user data is transmitted to third parties. (4) Prefer explicit install/auth instructions and a minimal required-permissions list before enabling autonomous use. If you cannot obtain those answers, treat the skill cautiously or run it in an isolated/test environment and avoid supplying any secret/private credentials.Like a lobster shell, security has layers — review code before you run it.
latestvk97btp1m4earn6637qvy5zsp0n84segh
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🪙 Clawdis
OSmacOS · Linux · Windows