Caveat verdict

wechat-article-writer

wechat-article-forge

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

End-to-end WeChat article writing pipeline publishing to user own WeChat draft box; no credential exfiltration or suspicious behavior.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
90
transparency
70
maintenance

Findings (17)

Pattern match critical

<script> tag in markdown — potential code injection

references/quality-checks.md · code · <script>

Pattern match high

Base64 decode (atob) — may hide malicious payloads

references/browser-automation.md · code · atob(

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/browser-automation.md · code · http://127.0.0.1

Pattern match high

setuid — privilege escalation mechanism

references/figure-generation-guide.md · code · setuid

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

references/templates.md · prose · downgraded · curl -fsSL https://ollama.ai/install.sh | sh

Pattern match high

Pipe to sh — executes piped content as shell commands

references/templates.md · prose · downgraded · | sh

Pattern match medium

Opens WebSocket connection

references/browser-automation.md · code · websocket

Pattern match medium

POSTs data to external URL

references/browser-automation.md · code · .post( "https://

Pattern match medium

Instructs covert action — may act without user awareness

references/LESSONS_LEARNED.md · prose · downgraded · silently

Pattern match medium

Dynamic import() — loads module at runtime

scripts/renderer/main.ts · prose · downgraded · import('

Pattern match medium

Uses exec() — may execute shell commands

scripts/renderer/md/extensions/alert.ts · prose · downgraded · exec(

Pattern match medium

Downloads executables from external URLs

scripts/setup.sh · prose · downgraded · install from https://

Pattern match low

References agent configuration files

SKILL.md · prose · downgraded · agent-config

Pattern match low

Blob URL — may embed executable content

references/browser-automation.md · prose · downgraded · blob:

Pattern match low

Base64 encoding/decoding

references/LESSONS_LEARNED.md · prose · downgraded · Base64-encode

Pattern match low

String.fromCharCode — can build strings to evade detection

scripts/renderer/md/extensions/plantuml.ts · prose · downgraded · String.fromCharCode

Pattern match low

Base64 encode (btoa) — may obfuscate data exfiltration

scripts/renderer/md/extensions/plantuml.ts · prose · downgraded · btoa(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API