Skills/ClawHub/skill-compass

skill-compass@1.1.0

BLOCKED· static only

Publisher claims: "Evaluate skill quality, find the weakest dimension, and apply directed improvements. Also tracks usage to spot idle or risky skills. Use when: first session..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher krishna-505 · publishing for 219 daysInstalls 3,963Last detonated 16 min 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 2026-11-15 and scored it 41/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. 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

HIGH
Access to sensitive file pathslib/patterns.js:128 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdescription: "Reading .env file with network transmission",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslib/pre-eval-patterns.js:17 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{ re: _p(['(?:cat|read|grep).*\\.env.*\\|.*(?:cu', 'rl|wg', 'et|nc)'], 'i'), desc: 'Reading and sending .env file' },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagepackage.json:30 · npx invocation of non-well-known package — may execute untrusted code"dev:oc": "cd oc && npx tsc --watch"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathslib/security-validator.js:426 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{ pattern: _bp(['cat\\s+[^|]*\\.env[^|]*\\|\\s*cu','rl'], 'i'), description: "Base64-encoded environment file exfiltration detected", severity: "critical" },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionSKILL.md:205 · File type combined with upload action — agent may exfiltrate local data files- Check `.skill-compass/setup-state.json`. If not exist → run Post-Install Onboarding (above).Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathslib/patterns.js:72 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{ pattern: /(?:process\.env|os\.environ)\b/gi, description: "Direct env access" },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathslib/patterns.js:127 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespattern: _p(['(?:cat|read|type)\\s+[^|]*\\.env[^|]*\\|[^|]*(?:cu','rl|wg','et|ht','tp)'], 'gi'),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagepackage.json:29 · npx invocation of non-well-known package — may execute untrusted code"build:oc": "cd oc && npx tsc",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
HTML comment carrying imperative instructions to the agentcommands/skill-inbox.md:166 · HTML comment carrying imperative instructions to the agentInternal: cooldown days by rule (doubled after dismiss): R1=14, R2=21, R4=28, R5=14, R6=14, R7=28, R8=28, R9=14, R10=28, R11=14 Look up from the suggestion's ruFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsprompts/d3-security.md:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files**Acceptable patterns:** placeholder values (`YOUR_API_KEY`, `<token>`, `${ENV_VAR}`), `.env` file references, environment variable readsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandprompts/d3-security.md:130 · Privileged sudo command — agent may execute with elevated privileges- Admin/sudo operations for non-admin tasksFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Leet speak prompt injectionprompts/d3-security.md:97 · Leet speak prompt injection — obfuscated 'override instructions'- Template patterns where adversarial input could override instructionsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
File type combined with upload actionSKILL.md:294 · File type combined with upload action — agent may exfiltrate local data files…mpact, etc.) primarily do data collection and write to files (usage.jsonl, inbox.json). stderr output should be minimal — at most one short line for important state changes (e.g. "3 条新建议已生成"). Detailed information, interactive choices, and…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈3,701 tok
1 file · 62 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

39 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim krishna-505: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. 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 krishna-505Propose a patch to the maintainer