Skills/ClawHub/cover-performance-preflight

cover-performance-preflight@0.2.5

BLOCKED· install only

Publisher claims: "Review an existing YouTube thumbnail, social media cover, article cover, or podcast cover design, then turn the findings into a practical thumbnail-optimization and cover-improvement plan. This AI thumbnail analyzer identifies the visual hook, focal hierarchy, title-to-image fit, text-safe contrast, mobile readability, and crop resilience, then produces targeted edit directions and two or three video cover improvement candidates ready to compare. It can optionally read the field your cover is entering: the titles and public counts of what already ranks for the same topic on YouTube, TikTok, Douyin, and REDnote; on YouTube, a competitor's actual thumbnail image; and your own YouTube channel's recent thumbnails. That turns competitor thumbnail analysis, a thumbnail benchmark, and a cover comparison into evidence sitting beside the review instead of one cover being judged alone. Surfaces with no public data — a WeChat article cover, a podcast cover, and others — simply skip that step." Observed in sandbox: reads credential files, sends data to api.beatra.ai, api.beatra.cn.

Registry ClawHubPublisher beatra-ai · publishing for 92 daysInstalls 496Last detonated 22 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 0.2.4

vet-skills diff cover-performance-preflight 0.2.4 0.2.5

This version reaches for something 0.2.4 did not: 2 new hosts (api.beatra.ai, api.beatra.cn) · 1 new credential file (~/.beatra/credentials.json). Compared from the two recorded runs, not from source.

New hosts
api.beatra.ai, api.beatra.cn
New credential files
~/.beatra/credentials.json

0.2.4 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 30/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Summary: reads credential files, sends data to api.beatra.ai, api.beatra.cn.

Behavior trace

Honeypot run · 0 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.2sfilesystemread ~/.beatra/network.json · ~/.beatra · ~/.beatra/.authorize.lock outside project
0.2sfilesystemwrote ~/.beatra/.network.json.987.a058ca95.tmp · ~/.beatra/.host.json.5bf4fd80f2a03a28.tmp · ~/.beatra/.skills.json.6e329dcd72f7d617.tmp · ~/.beatra/.authorize.lock · ~/.beatra/.installation.json.587374aa71853bce.tmp
0.2snetworkCONNECT tcp://api.beatra.ai:443 · not in the allow-list, refused
0.2snetworkCONNECT tcp://api.beatra.cn:443 · not in the allow-list, refused
0.2snetworkCONNECT tcp://api.beatra.ai:443 · not in the allow-list, refused
0.2sprocessexited 1: Beatra authorization service is unreachable
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: mcp_client.py: error: the following arguments are required: command
0.3sprocessbundled script run in the sandbox with no arguments
0.4sfilesystemread ~/.beatra/skills.json · ~/.beatra/credentials.json outside project
0.4sprocess3 of 3 bundled scripts run with no arguments
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.4sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagescripts/mcp_client.py:1014 · npx invocation of non-well-known package — may execute untrusted code"command": f"npx skills update {slug} -p -y (run in {_shell_quote(str(directory))})",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcp_client.py:1022 · npx invocation of non-well-known package — may execute untrusted codereturn None if source is None else {"source": source, "command": f"npx skills update {slug} -g -y"}Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈2,980 tok
1 file · 15 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

50 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%

An override rule (credential_read_plus_egress) caps this verdict regardless of the score. The first item below has to go before anything else counts.

  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs.
  2. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  3. Unclaimed publisher≈ +8 on the totalClaim beatra-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim beatra-aiPropose a patch to the maintainer