persistent-code-terminal@1.2.0
CAUTION· static onlyPublisher 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.
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 onlyThis 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
- `给 <project> 项目 <instruction>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- `codex-exec.sh "<instruction>"` for Codex-driven workFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- 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.- `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.- `{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.- In OpenClaw routing, map `codex <instruction>` to:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- `auto.sh --max-retries 3 --instruction "<instruction>"`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.print_fix "Ubuntu/Debian: sudo apt install tmux"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- `./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.sudo apt-get install -y tmux shellcheck shfmt batsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- `给<project>项目:<instruction>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- `给<project>项目:<instruction>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.sudo apt-get updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- `给 <project> 项目 <instruction>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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%- 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.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.