Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
TGA Analyze
v1.0.0Logs into TGA (hortorgames), parses projectId and dashboardId from panel URL, downloads report zip via API, unzips to tga-downloads/, and analyzes all xlsx f...
⭐ 0· 25·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The code and SKILL.md match the described purpose: login, start a download task, poll progress, and save the report zip for downstream analysis. However, the skill requires a local .env with TGA_LOGIN_NAME, TGA_ENCRYPTED_PASSWORD, and TGA_COOKIES (explicitly documented in SKILL.md), yet the registry metadata lists no required env vars. That mismatch is unexpected and should have been declared.
Instruction Scope
Instructions are narrowly scoped to the TGA site flow (parse project/dashboard IDs, run the included node script to login/download, unzip, then analyze xlsx with pandas). The runtime guidance explicitly reads/writes files in the skill directory (.env and .tga-token). This is functionally consistent with the task but it asks the user to paste full browser cookie strings (sensitive) and to place them in a local file — a surface for accidental credential exposure.
Install Mechanism
This is instruction-only plus an included node script; there is no install spec that downloads arbitrary artifacts. No external install URLs or archive extraction were found in the provided files.
Credentials
The skill requires sensitive values (TGA_LOGIN_NAME, TGA_ENCRYPTED_PASSWORD, and TGA_COOKIES) documented in SKILL.md and used by the script, but the registry metadata declared none. Requesting full browser cookies is high-sensitivity and storing them in a .env inside the skill directory increases risk of accidental leakage. The skill caches an access token in .tga-token in the skill directory — expected for convenience but still sensitive.
Persistence & Privilege
always:false and normal autonomous invocation settings. The skill writes only to files inside its own directory (.tga-token) and reads .env from its directory — it does not request system-wide changes or modify other skills' config. No 'always: true' or other elevated persistence was requested.
What to consider before installing
This skill's behavior (login → start report → poll → download) is coherent, but the SKILL.md requires you to create a .env containing TGA_LOGIN_NAME, TGA_ENCRYPTED_PASSWORD, and a full browser cookie string (TGA_COOKIES). The registry metadata not listing these required credentials is an inconsistency; treat that as a red flag. Before installing or using: (1) review the included scripts yourself to confirm they only contact tga-web.hortorgames.com (they do in the provided code), (2) avoid committing the .env to source control and store it securely, (3) consider running the skill in an isolated environment or container, (4) prefer shorter-lived tokens if possible rather than pasting full browser cookies, and (5) if you cannot safely provide cookies/passwords, do not use the skill. If you want a safer integration, ask the author to declare required env vars in the registry metadata and to support providing credentials via the platform's secret storage rather than a plaintext .env in the skill directory.scripts/tga.js:42
File read combined with network send (possible exfiltration).
About static analysis
These patterns were detected by automated regex scanning. They may be normal for skills that integrate with external APIs. Check the VirusTotal and OpenClaw results above for context-aware analysis.Like a lobster shell, security has layers — review code before you run it.
latestvk973e66b2jf4xrakr0w6g1tew9844qta
License
MIT-0
Free to use, modify, and redistribute. No attribution required.