Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
test
v1.0.0Expert AI agent specializing in carousel growth engine. From The Agency (github.com/msitarzewski/agency-agents).
⭐ 0· 35·0 current·0 all-time
by@zhouqkt
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The skills' required external services (Gemini for image gen and Upload-Post for publishing/analytics) match the stated purpose. However the registry metadata claims no required environment variables or binaries, while the SKILL.md and AGENTS.md explicitly require GEMINI_API_KEY, UPLOADPOST_TOKEN, UPLOADPOST_USER and Playwright — this mismatch is incoherent and unexpected.
Instruction Scope
SKILL.md instructs full autonomous operation: Playwright web scraping of arbitrary target URLs, generating images with Gemini, publishing directly to TikTok/Instagram, fetching analytics, updating a persistent learnings.json, and auto-scheduling future runs without asking the user. It also requires running various scripts (generate-slides.sh, analyze-web.js, publish-carousel.sh, check-analytics.sh) and vision verification steps. Those scripts are referenced but not included in the package, and the document tells the agent to modify scheduling (cron) and write persistent state — scope creep beyond a passive helper.
Install Mechanism
There is no install spec (instruction-only), but the runtime expects Playwright (and implicitly Python tooling, 'uv', and possibly other binaries) and several local scripts. The package lacks those script files. Absence of an install mechanism combined with explicit calls to platform tools is an operational inconsistency that increases risk and ambiguity.
Credentials
The environment secrets referenced in the documentation (GEMINI_API_KEY, UPLOADPOST_TOKEN, UPLOADPOST_USER) are appropriate for the claimed behavior, but the registry metadata lists no required env vars — a clear mismatch. Additionally, the skill asks to publish posts and access analytics for accounts tied to those tokens; granting those tokens gives the skill full publishing/analytics ability on the accounts, so only sandbox/test credentials should be used if you proceed.
Persistence & Privilege
The skill's autonomy rules require 'zero confirmation', persistent storage of learnings (/tmp/carousel/learnings.json), and self-scheduling (cron). While always:false, the instructions explicitly tell the agent to schedule future runs and modify system scheduling — that implies making persistent system changes and recurring network actions without per-run consent, which is a notable privilege and risk.
What to consider before installing
This skill claims to autonomously scrape websites, generate images, publish to social platforms, fetch analytics, and schedule itself — but the package metadata contradicts the SKILL.md (no declared env vars or scripts), and the scripts and install steps referenced are missing. Before installing: (1) do not provide real Gemini or Upload-Post credentials — use sandbox/test accounts if you want to try; (2) ask the publisher for the missing scripts and an install spec or clear instructions for required binaries; (3) confirm you are comfortable with autonomous publishing and cron scheduling (it will post without asking); (4) prefer running it in an isolated environment or VM first; (5) if you need only analysis/generation help, consider a non-autonomous alternative that requires explicit confirmation before publishing.Like a lobster shell, security has layers — review code before you run it.
latestvk974yjzs32fscvp1r3v27bfqx984kxwr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🎠 Clawdis