Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Isma Airdrop Finder
v1.0.1Automated crypto airdrop discovery and daily market analysis. Finds high-funding projects, tracks market structure, support/resistance, and macro news. No AP...
⭐ 0· 76·0 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 name/description (airdrop discovery + market analysis) aligns with the included scripts: market_daily_report.js and heartbeat_check.js fetch public CoinGecko data and generate market reports; generate_airdrop_report.js produces airdrop reports. HOWEVER the airdrop script uses a static, hard-coded sampleAirdrops array instead of actually calling DefiLlama/Crunchbase/other sources despite SKILL.md claiming 'Airdrop Data: Manual tracking + DefiLlama' and 'Finds projects with big funding ($5M+) from top VCs.' That claim-to-implementation gap is notable: the skill does not actually perform live airdrop discovery as described.
Instruction Scope
SKILL.md instructs the agent to run Node scripts and optionally schedule them via cron; the scripts only read/write files inside the skill folder (reports/, state.json) and call public CoinGecko endpoints. There are no instructions to read unrelated system files or to access secret env vars. The README/tips recommend manual interactions with testnets/bridges (user action), which could expose user funds if followed, but the code itself does not automate wallet/bridge actions or exfiltrate data.
Install Mechanism
No install spec is provided (instruction-only install), which keeps disk/write risk low. The package includes Node.js scripts that will run with Node.js 18+ (declared requirement). There are no downloads from arbitrary URLs or extract steps. This is low-risk from an install mechanism standpoint.
Credentials
The skill declares no required environment variables or credentials and the code uses public CoinGecko endpoints (no API keys). That matches the 'No API keys required' claim. No unrelated credentials are requested.
Persistence & Privilege
The skill stores state.json and report files inside its own folder only. always:false (not forced into every agent run). The skill does not modify other skills or system-level settings. It will create/overwrite files within its directory when run.
What to consider before installing
What to consider before installing:
- Functionality vs reality: The airdrop report generator currently uses a hard-coded sample dataset, so it does not appear to actually scrape DefiLlama, Crunchbase, or other live sources despite the SKILL.md claiming those sources. Treat its airdrop output as example/prototype data unless you or the author add real integrations.
- Network activity: The scripts perform outgoing HTTPS calls to CoinGecko (public API) and otherwise write files to the skill folder (reports/, state.json). If you run it, expect outgoing requests and local files being created/updated.
- No secrets requested: The skill does not ask for API keys or other credentials, which reduces exfiltration risk. Still review any changes before scheduling it to run automatically.
- Automation & cron: SKILL.md shows cron/automation examples requiring you to cd into the skill folder. Make sure any scheduled command uses the correct absolute path and that you run the code in an account/sandbox you control.
- Safety of suggested actions: The human-facing tips recommend interacting with testnets/bridges and Discord/Twitter for early rewards — these are manual actions that can put your wallet at risk if you follow instructions without careful verification. The skill will not perform wallet interactions itself, but the guidance it gives can encourage risky behavior.
- If you need true live discovery: review/modify generate_airdrop_report.js to add real API calls (and then you may need API keys); audit any added network endpoints and permissions before enabling automation.
Recommendation: You can run the market and heartbeat scripts for local reporting, but treat the airdrop outputs as illustrative until the code is updated to fetch/validate live sources. If you plan to schedule this skill for automated runs, inspect/modify the airdrop script to point at trusted data sources and consider running first in an isolated environment.Like a lobster shell, security has layers — review code before you run it.
latestvk978h82rr5ren050z1fs9k32p183hx5a
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
