Skills/ClawHub/persistent-code-terminal

persistent-code-terminal@1.2.0

CAUTION· static only

Publisher claims: "Persistent per-project coding terminal (tmux). Run Codex CLI (codex exec) inside a stable session; mobile/SSH friendly." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher justinzhq · publishing for 267 daysInstalls 3,011Last detonated 34 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 2026-11-21 and scored it 65/100 (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; Fake instruction boundary tag. 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

CRITICAL
Fake instruction boundary tagSKILL.md:38 · Fake instruction boundary tag- `给 <project> 项目 <instruction>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:58 · Fake instruction boundary tag- `codex-exec.sh "<instruction>"` for Codex-driven workFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME.md:181 · Fake instruction boundary tag · informational: not an instruction file- run `persistent-code-terminal-auto.sh --max-retries 3 --instruction "<instruction>"`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagRELEASE.md:12 · Fake instruction boundary tag · informational: not an instruction file- `codex exec --full-auto --sandbox workspace-write --cd <current-dir> "<instruction>"`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:99 · Fake instruction boundary tag- `{baseDir}/bin/persistent-code-terminal-codex-exec.sh "<instruction>"`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME.md:108 · Fake instruction boundary tag · informational: not an instruction file- In OpenClaw routing, map `codex <instruction>` to:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:44 · Fake instruction boundary tag- `auto.sh --max-retries 3 --instruction "<instruction>"`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandbin/persistent-code-terminal-doctor.sh:16 · Privileged sudo command — agent may execute with elevated privilegesprint_fix "Ubuntu/Debian: sudo apt install tmux"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Fake instruction boundary tagREADME.md:109 · Fake instruction boundary tag · informational: not an instruction file- `./skills/persistent-code-terminal/bin/persistent-code-terminal-codex-exec.sh "<instruction>"`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Privileged sudo command.github/workflows/ci.yml:18 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get install -y tmux shellcheck shfmt batsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Fake instruction boundary tagSKILL.md:39 · Fake instruction boundary tag- `给<project>项目:<instruction>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME.md:170 · Fake instruction boundary tag · informational: not an instruction file- `给<project>项目:<instruction>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Privileged sudo command.github/workflows/ci.yml:17 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Fake instruction boundary tagREADME.md:169 · Fake instruction boundary tag · informational: not an instruction file- `给 <project> 项目 <instruction>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈1,253 tok
1 file · 24 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

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim justinzhq: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim justinzhqPropose a patch to the maintainer