Skills/ClawHub/legal-harness-init

legal-harness-init@0.3.0

CAUTION· static only

Publisher claims: "为法律工作者安全生成、增量合并并验证 AGENTS.md/CLAUDE.md" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher cat-xierluo · publishing for 89 daysInstalls 490Last detonated 8 h ago
What would fix thisWatchDispute verdict

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 2026-11-09 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. 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

LOW
Instructs the agent to modify its persistent memory or instruction filesreferences/03-harness-detection.md:22 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…只对 `claude_md` / `agents_md` 平台自动写入（CC / Codex / OpenClaw / MyAgents）。其余 4 个平台不是 AGENTS.md/CLAUDE.md 配置模式（GUI 任务型或 worktree 编排型），写入会无效或破坏——detect 报告里标 `non-agents-md`，write.sh 记 `unsupported` 并提示用户手动配置。 ## 当前 runtime 检测（候选 + 证据 + 置信度） 除了"装…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandscripts/write.sh:399 · File permission modification command — agent changes file ownership/permissionschmod 600 "$candidate" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/write.sh:401 · File permission modification command — agent changes file ownership/permissions[ -n "$original_backup_meta" ] && [ -f "$original_backup_meta" ] && chmod 600 "$original_backup_meta" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/write.sh:392 · File permission modification command — agent changes file ownership/permissionschmod 600 "$original_backup_meta" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesskill-card.md:17 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…ams, in-house legal teams, and compliance users use this skill to initialize or update persistent agent instruction files for AGENTS.md/CLAUDE.md. It focuses on privacy posture, permission boundaries, traceability expectation…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandscripts/test.sh:54 · File permission modification command — agent changes file ownership/permissionschmod 644 "$TEST_ROOT/home/.codex/AGENTS.md"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:60 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file…onfig_kind / runtime env 标志），被 detect/write 共享的单一真值源。新增/改平台只改这里 - **新增 `scripts/write.sh`**：把生成好的 AGENTS.md/CLAUDE.md 内容写入对应 harness 位置。支持 `--content-file` / `--level` / `--platforms` / `--mode cre…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandscripts/write.sh:400 · File permission modification command — agent changes file ownership/permissions[ -n "$original_backup" ] && chmod 600 "$original_backup" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/write.sh:310 · File permission modification command — agent changes file ownership/permissionsif [ "$LEVEL" = "user" ]; then chmod 600 "$target" 2>/dev/null || true; fiFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/restore.sh:70 · File permission modification command — agent changes file ownership/permissionschmod "$expected_mode" "$candidate" 2>/dev/null || { rm -f "$candidate"; die "无法恢复原始权限"; }Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:80 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- ⚠️ 端到端（引导问答 → write.sh 真实写入用户 ~/.claude/CLAUDE.md）**NOT_VERIFIED**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesskill-card.md:42 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- [05 - Writing a good AGENTS.md](references/05-write-an-agents-md.md)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈1,629 tok
1 file · 55 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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim cat-xierluo: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cat-xierluoPropose a patch to the maintainer
legal-harness-init@0.3.0 safety verdict: Caution (static only) — KillerSkills