Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Genviral Skill

v1.0.0

Complete genviral Partner API automation. Create and schedule posts (video + slideshow) across TikTok, Instagram, and any supported platform. Includes slides...

1· 358·0 current·0 all-time
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
Name and description match the files and commands: this is a Genviral Partner API wrapper and needs bash/curl/jq to call the Partner API. However the metadata claims 'Required env vars: none' and 'Primary credential: none' while SKILL.md and defaults.yaml clearly reference GENVIRAL_API_KEY (and an optional GENVIRAL_WORKSPACE_DIR). That mismatch is an incoherence the user should be aware of.
Instruction Scope
SKILL.md instructs the agent to call the Partner API, generate/upload media, and read/write workspace files (workspace/performance/log.json, hook-tracker.json, etc.) — all consistent with the stated purpose. It also references a vision/image tool for image assessment and requires human visual review as a hard gate. No instructions request unrelated system secrets or arbitrary host files. The one noteworthy instruction-surface risk: the skill includes a self-updater (scripts/update-skill.sh) and README documents an auto-update flow; that updater could fetch and replace skill code if run.
Install Mechanism
There is no formal install spec in the registry (no package downloads at install time), which is low-risk. But the bundle contains scripts (scripts/genviral.sh and scripts/update-skill.sh). The README documents a git clone install and an updater script that can check/apply updates. If the updater fetches code from the network (likely GitHub), running it transfers execution trust to remote code updates — an expected convenience but an operational risk if the remote repo is compromised or the updater is run automatically without review.
!
Credentials
The runtime clearly requires an API key (GENVIRAL_API_KEY) to call the Partner API and optionally GENVIRAL_WORKSPACE_DIR, but the registry metadata did not declare any required env vars or primary credential. That discrepancy is significant: the skill will prompt for/use a secret (API key) even though the metadata says none are needed. No other unrelated secrets are requested in the docs.
Persistence & Privilege
always:false (not force-included) and normal autonomous invocation settings. The skill writes only to its own workspace/ directory (declared user-owned in README). The updater modifies skill-owned files (SKILL.md, scripts, docs) per README — this is expected for a self-updating skill but is a privilege the user should consciously accept. The skill does not request system-wide config or other skills' credentials.
What to consider before installing
This skill appears to do what it says (wrap the Genviral Partner API) but has a few red flags you should address before installing or running it: - The SKILL.md and defaults.yaml require GENVIRAL_API_KEY (and optionally GENVIRAL_WORKSPACE_DIR), but the registry metadata claims no required env vars — treat that as a metadata/packaging error. Expect to supply your Genviral API key to use it. - Inspect scripts/genviral.sh and scripts/update-skill.sh yourself before running. The updater can fetch and apply remote code; verify where it pulls updates from and whether it does automatic network operations. If you don't want remote code pulled, do not run the updater or remove/disable it. - Run the skill in a constrained environment (container or isolated user account) the first time so it can only access the files you intend. Monitor network calls or run it with network access disabled if you only want to inspect behavior. - Backup any important data; the skill writes to workspace/, which the README says is user-owned, but you should confirm and set workspace dir to a safe location you control. - Confirm the GitHub homepage/source (https://github.com/fdarkaou/genviral-skill) is legitimate and matches the files you received; prefer installing via a pinned commit or review the repo history to reduce supply-chain risk. If you want, I can (a) list the exact files/lines to review in scripts/update-skill.sh and scripts/genviral.sh for network fetches/execution, or (b) help craft safe commands to run the skill in an isolated container for testing.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🎬 Clawdis
Binscurl, jq, bash
latestvk97cvtjhrz5aq6wtdzhq46gs9s8266a6
358downloads
1stars
1versions
Updated 8h ago
v1.0.0
MIT-0

genviral Partner API Skill

TL;DR: Wraps genviral's Partner API into 50+ bash commands. Core flow: get-pack → analyze images (metadata + vision) → generate with pinned_imagesrender → visual review (hard gate) → create-post → log to workspace/performance/log.json. Studio AI: studio-modelsstudio-generate-image (sync) or studio-generate-videostudio-video-status --poll (async). Auth via GENVIRAL_API_KEY. Config in defaults.yaml. Instance data in workspace/.

What This Skill Does

  • Multi-Platform Posting: Video or slideshow posts across TikTok, Instagram, YouTube, Pinterest, LinkedIn, Facebook
  • Studio AI Generation: Generate images (sync) and videos (async) via AI models through the API
  • File Management: Upload videos/images to genviral's CDN
  • AI Slideshow Generation: Photo carousels from prompts, rendered to images
  • Template System: Reusable slideshow structures, convert winners to templates
  • Pack Management: Image packs as slideshow backgrounds
  • Analytics: KPIs, post-level metrics, tracked accounts, refresh triggers
  • Niche Intelligence: One-call trend research (trend-brief) for hashtags, sounds, creators, posting windows, and hook angles
  • Content Pipeline: Full automation from prompt to posted content
  • Performance Tracking: Post log, hook tracking, weekly review
  • Hook Library: Maintain and evolve a library of proven content hooks

How It Works

  1. Generate or upload media
  2. Create a post targeting one or more accounts
  3. Schedule or publish (for TikTok slideshows, optionally save as drafts so you can add trending audio before publishing — music selection requires human judgment for best results)
  4. Track performance via analytics
  5. Learn and optimize

All configuration in defaults.yaml. Secrets via environment variables. Everything posted shows up in the Genviral dashboard.

First-Time Setup

If fresh install, read docs/setup.md and walk the user through onboarding conversationally:

  1. Set API key and verify it works
  2. List accounts and pick which to post to
  3. Discuss image strategy (existing packs, create new, generate per post, or mix)
  4. Optionally set up product context and brand voice together

No hardcoded defaults. Ask the user what they prefer and adapt. Everything done through this skill shows up in the Genviral dashboard, so the user always has full visibility and control.

File Structure

genviral/
  SKILL.md                  # This file (kernel + routing)
  README.md                 # Human-facing overview
  defaults.yaml             # API config and defaults

  docs/
    setup.md                # Onboarding guide (conversational, 5 phases)
    api/
      accounts-files.md     # accounts, upload, list-files
      posts.md              # create-post, update-post, retry, list, get, delete
      slideshows.md         # generate, render, review, update, regenerate, duplicate, list + text styles
      packs.md              # pack CRUD + smart image selection (MANDATORY reading for any pack workflow)
      templates.md          # template CRUD + create-from-slideshow
      analytics.md          # all analytics commands
      studio.md             # Studio AI: generate images/videos, list models, poll status
      subscription.md       # subscription status, credits, tier
      pipeline.md           # content pipeline, performance loop, CTA testing, platform tips
      errors.md             # error codes and troubleshooting
    references/
      analytics-loop.md     # Full analytics feedback loop and weekly review process
      competitor-research.md # How to research competitors
    prompts/
      slideshow.md          # Prompt templates for slideshow generation
      hooks.md              # Prompt templates for hook brainstorming

  workspace/                # All instance/customer data (override with GENVIRAL_WORKSPACE_DIR)
    content/
      scratchpad.md         # Working content plan and drafts
      calendar.json         # Upcoming planned posts
    context/
      product.md            # Product description, value props, target audience
      brand-voice.md        # Tone, style, do's and don'ts
      niche-research.md     # Platform research for the niche
    hooks/
      library.json          # Hook instances (grows over time, tracks performance)
      formulas.md           # Hook formula patterns and psychology
    performance/
      log.json              # CANONICAL post record (single source of truth)
      hook-tracker.json     # Hook and CTA tracking with metrics (the feedback loop)
      insights.md           # Agent learnings from performance data
      weekly-review.md      # Weekly review notes
      competitor-insights.md # Competitor research findings

  scripts/
    genviral.sh             # Main API wrapper (all commands)
    update-skill.sh         # Self-updater

Command Routing

Load only what you need for the current task:

TaskRead
Account discovery, file uploaddocs/api/accounts-files.md
Create, update, list, delete postsdocs/api/posts.md
Slideshow generation, rendering, editing, text stylesdocs/api/slideshows.md
Pack management, image selection (ANY pack workflow)docs/api/packs.md
Template creation and managementdocs/api/templates.md
Analytics queries and target managementdocs/api/analytics.md
Studio AI: generate images, videos, list modelsdocs/api/studio.md
Subscription: check credits, tier, renewal datesdocs/api/subscription.md
Research a specific niche quickly (trend + competitors + hooks)docs/api/analytics.md, docs/references/competitor-research.md, docs/prompts/hooks.md
Full content pipeline, performance loop, CTA testingdocs/api/pipeline.md
Error codes, troubleshootingdocs/api/errors.md

Niche Research Mode (When user asks to research a niche)

When asked things like "research this niche", "find what works in this niche", or "give me niche intelligence":

  1. Run trend-brief first for the niche keyword (7d baseline, then 24h for freshness if needed).
  2. Extract and report: top hashtags, top sounds, top creators, posting windows (UTC), recommended hook angles.
  3. Run competitor deep-dive using docs/references/competitor-research.md (3-5 accounts minimum).
  4. Produce a short actionable output with:
    • 3 hook angles to test
    • 2 CTA suggestions
    • 2 best posting windows
    • 5 hashtags to start with
    • 1 "gap to exploit" insight
  5. Save findings to workspace/performance/competitor-insights.md and use them in subsequent content prompts.

Non-Negotiable Rules

These apply regardless of what docs you've loaded:

  1. ALWAYS use pinned_images when generating a slideshow with a pack. Never call generate with just --pack-id — the server will pick random images. Read docs/api/packs.md before any pack workflow.

  2. ALWAYS visually review every rendered slide before posting. If any slide fails readability, fix it. This is a hard gate — not a suggestion.

  3. ALWAYS log to workspace/performance/log.json immediately after posting. This is the canonical record.

  4. ALWAYS add a hook-tracker entry after posting. No tracking = no learning.

  5. Never use em-dashes in any generated content.

  6. Respect workspace/ — all instance data lives here. Do not write state files to the skill root.

Script Usage

/path/to/genviral/scripts/genviral.sh <command> [options]

Requires GENVIRAL_API_KEY as an environment variable (format: public_id.secret). Loads defaults from defaults.yaml. Set GENVIRAL_WORKSPACE_DIR to override the workspace path (defaults to workspace/ relative to the skill dir).

Auto-Updates

This skill includes a self-updater that keeps skill-owned files in sync with the latest version from fdarkaou/genviral-skill.

bash scripts/update-skill.sh           # check + apply if updates available
bash scripts/update-skill.sh --dry-run # preview only, no changes
bash scripts/update-skill.sh --force   # force re-apply even if already current

What gets updated (skill-owned): SKILL.md, scripts/, docs/ (all subdirs)

What never gets touched (user-owned): workspace/ — your data, context, hooks, and performance logs are always preserved.


Notes

  • Works with any platform genviral supports (TikTok, Instagram, etc.)
  • Supports both video and slideshow posts
  • Works with hosted and BYO accounts
  • Posts can be scheduled or queued for immediate publishing
  • TikTok slideshow drafts: use post_mode: MEDIA_UPLOAD to save to drafts inbox for audio addition

Comments

Loading comments...