Skills/ClawHub/ernie-image-radeon

ernie-image-radeon@1.0.1

CAUTION· static only

Publisher claims: "FREE ERNIE-Image text-to-image generation powered by AMD Radeon Cloud. No API key required. Generate AI images via ERNIE-Image and ERNIE-Image-Turbo models r..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher aiwork4me · publishing for 192 daysInstalls 797Last detonated 33 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-22 and scored it 67/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Fake instruction boundary tag; HTTP URL with a raw public IP address. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
URL using a raw public IP addressscripts/generate.py:31 · URL using a raw public IP address — may bypass domain-based filteringRADEON_BASE_URL = "http://134.199.132.159/ocr/v1"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Fake instruction boundary tagSKILL.md:95 · Fake instruction boundary taguv run scripts/generate.py "<PROMPT>" --model ERNIE-Image --steps 16 --guidance 3.5Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:89 · Fake instruction boundary taguv run scripts/generate.py "<PROMPT>" --n 4 --output ./output_dirFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
HTTP URL with a raw public IP addressscripts/generate.py:31 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot nameRADEON_BASE_URL = "http://134.199.132.159/ocr/v1"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Fake instruction boundary tagSKILL.md:101 · Fake instruction boundary taguv run scripts/generate.py "<PROMPT>" --seed 42Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:83 · Fake instruction boundary taguv run scripts/generate.py "<PROMPT>" --model ERNIE-Image-Turbo --size 1024x1024Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈1,627 tok
1 file · 4 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

13 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim aiwork4me: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. HTTP URL with a raw public IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  3. URL using a raw public IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim aiwork4mePropose a patch to the maintainer