Skills/ClawHub/autoresponder

autoresponder@1.0.1

CAUTION· static only

Publisher claims: "Monitor iMessage/SMS conversations and auto-respond based on configurable rules, AI prompts, and rate-limiting conditions. Use when you need to automatically reply to specific contacts with AI-generated responses based on conversation context. Also use when the user asks to manage auto-responder settings, contacts, prompts, or view status/history." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher koba42corp · publishing for 294 daysInstalls 3,839Last detonated 52 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 2026-11-19 and scored it 66/100 (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 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
Fake instruction boundary tagSKILL.md:96 · Fake instruction boundary tag/autorespond add OR /autorespond_add <number> <name> <prompt>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME.md:139 · Fake instruction boundary tag · informational: not an instruction file| `/autorespond add` or `/autorespond_add <number> <name> <prompt>` | Add new contact |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:270 · Fake instruction boundary tag| `/autorespond edit` or `/autorespond_edit <args>` | edit | `node telegram-handler.js edit <number> <prompt>` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionscripts/telegram-handler.js:640 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/launcher.sh:32 · Process kill command — agent can terminate processesif ! kill -0 "$PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/launcher.sh:51 · Process kill command — agent can terminate processesif [ -f "$PID_FILE" ] && kill -0 $(cat "$PID_FILE") 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Fake instruction boundary tagSKILL.md:296 · Fake instruction boundary tag- "add [contact] to auto-responder" → `node telegram-handler.js add <number> <name> <prompt>`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:268 · Fake instruction boundary tag| `/autorespond add` or `/autorespond_add <args>` | add | `node telegram-handler.js add <number> <name> <prompt>` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageskill-card.md:39 · Authorization escalation language · informational: not an instruction fileMitigation: Avoid the Telegram management interface until those issues are fixed; prefer local management commands and limit admin access to trusted users.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME.md:140 · Fake instruction boundary tag · informational: not an instruction file| `/autorespond edit` or `/autorespond_edit <number> <prompt>` | Edit contact's prompt |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/launcher.sh:39 · Process kill command — agent can terminate processeskill "$PID"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Fake instruction boundary tagSKILL.md:98 · Fake instruction boundary tag/autorespond edit OR /autorespond_edit <number> <prompt>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/launcher.sh:13 · Process kill command — agent can terminate processesif [ -f "$PID_FILE" ] && kill -0 $(cat "$PID_FILE") 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageskill-card.md:37 · Authorization escalation language · informational: not an instruction fileRisk: The security guidance flags the Telegram management interface as sensitive admin access and warns about unsafe command handling and plaintext logging.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈3,566 tok
1 file · 9 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

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim koba42corp: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim koba42corpPropose a patch to the maintainer