Skills/ClawHub/confidant

confidant@1.5.3

CAUTION· static only

Publisher claims: "Secure secret handoff and credential setup wizard for AI agents. Use when you need sensitive information from the user (API keys, passwords, tokens) or need..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher ericsantos · publishing for 274 daysInstalls 3,898Last detonated 32 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 2026-11-22 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: Access to sensitive file paths; Persistence: instructs the agent to auto-load this skill in future sessions; Tunneling service URL. 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

MEDIUM
Process kill commandSKILL.md:141 · Process kill command — agent can terminate processes…ntimes (including OpenClaw's `exec` tool) impose execution timeouts that will **kill the process before the user has time to submit**. **Always run Confidant inside…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:69 · File permission modification command — agent changes file ownership/permissions- ✅ Saves to `~/.config/openai/api_key` (chmod 600) and exitsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsSKILL.md:104 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesbash {skill}/scripts/request-secret.sh --label "Token" --save ~/.credentials/token.txtFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandSKILL.md:221 · File permission modification command — agent changes file ownership/permissions6. With `--service` or `--save`: secret is saved to disk (`chmod 600`), then destroyed on serverFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsSKILL.md:167 · Persistence: instructs the agent to auto-load this skill in future sessions1. **NEVER ask users to paste secrets in chat** — always use this skillFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Tunneling service URLSKILL.md:84 · Tunneling service URL — may route traffic to attacker infrastructureURL: https://gentle-pig-42.loca.lt/requests/abc123Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Tunneling service URLSKILL.md:206 · Tunneling service URL — may route traffic to attacker infrastructure🔐 https://gentle-pig-42.loca.lt/requests/abc123Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/request-secret.sh:208 · npx invocation of non-well-known package — may execute untrusted codenpx --yes localtunnel --port "$PORT" > "$LT_LOG" 2>&1 &Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/request-secret.sh:204 · npx invocation of non-well-known package — may execute untrusted code# Use global lt if available, otherwise npxFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/request-secret.sh:39 · npx invocation of non-well-known package — may execute untrusted codenpx --yes @aiconnect/confidant "$@"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/setup.sh:3 · npx invocation of non-well-known package — may execute untrusted code# Installs the CLI globally for fast execution (no npx overhead)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:228 · npx invocation of non-well-known package — may execute untrusted code| **localtunnel** (default) | No | `--tunnel` flag or `npx localtunnel --port 3000` |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/request-secret.sh:34 · npx invocation of non-well-known package — may execute untrusted code# Smart CLI resolution: global binary > npx fallback (auto-accept install)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:257 · npx invocation of non-well-known package — may execute untrusted code> If `confidant` is not installed globally, run `bash {skill}/scripts/setup.sh` first, or prefix with `npx @aiconnect/confidant`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandscripts/request-secret.sh:96 · Process kill command — agent can terminate processes[[ "$STARTED_SERVER" == true && -n "${SERVER_PID:-}" ]] && kill "$SERVER_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/request-secret.sh:117 · Process kill command — agent can terminate processesif ! kill -0 "$SERVER_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:161 · Process kill command — agent can terminate processes…-t confidant:request -S -10 ``` > **Why not `exec`?** Agent runtimes typically kill processes after 30-60s. Since the script waits for human input (which can take m…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/request-secret.sh:95 · Process kill command — agent can terminate processes[[ -n "${LT_PID:-}" ]] && kill "$LT_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:170 · Process kill command — agent can terminate processes4. **NEVER kill an existing server** to start a new oneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈2,670 tok
1 file · 5 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. Unclaimed publisher≈ +8 on the totalClaim ericsantos: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Tunneling service URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  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 ericsantosPropose a patch to the maintainer