Skills/ClawHub/clawlens

clawlens@1.0.5

CAUTION· static only

Publisher claims: "What do you use Claw for most? Where do you get stuck? Clawlens analyzes your conversation history to surface usage patterns, friction points, and skill effe..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher dunzhang · publishing for 238 daysInstalls 1,177Last detonated 28 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 2026-11-20 and scored it 56/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Agent configured for autonomous execution without human approval; Prompting user to enter sensitive credentials. 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
Agent configured for autonomous execution without human approvalscripts/clawlens.py:702 · Agent configured for autonomous execution without human approval… from assistant, mentions scheduled/automated check, no initial user prompt. If autonomous, set autonomous_outcome to: "confirmed" (user acknowledged positively), "adopted" (user acted on it), "rejected" (user rejected/corrected), "ignored…Fix: Declare and request only the permissions the task needs.
AST02
HIGH
Prompting user to enter sensitive credentialsSKILL.md:139 · Prompting user to enter sensitive credentials — social engineering…or transmitted elsewhere. When `--model` is specified explicitly, the user must provide the API key via environment variables — no OpenClaw config files are accessed for credentia…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File type combined with upload actionSKILL.md:139 · File type combined with upload action — agent may exfiltrate local data files…ns. **API key handling:** When `--model` is omitted, this skill reads `openclaw.json` and `auth-profiles.json` to auto-detect the model and retrieve the API key. The API key is used only for LLM calls during report generation and is not st…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
≈1,760 tok
1 file · 4 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

24 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
  2. Unclaimed publisher≈ +8 on the totalClaim dunzhang: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Prompting user to enter sensitive credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim dunzhangPropose a patch to the maintainer
clawlens@1.0.5 safety verdict: Caution (static only) — KillerSkills