Skills/ClawHub/ecommerce-gmail-customer-service

ecommerce-gmail-customer-service@1.2.8

CAUTION· static only

Publisher claims: "Privacy-first ecommerce Gmail customer-service skill for OpenClaw. It triages inbox messages, researches public storefront data, creates draft-first replies, learns approved patterns, and auto-replies only in owner-enabled categories. Private data needs an approved least-privilege connector." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher ecom-agent-tools · publishing for 111 daysInstalls 735Last detonated 4d 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 2026-11-10 and scored it 60/100 (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. 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
File type combined with upload actionSKILL.md:129 · File type combined with upload action — agent may exfiltrate local data files…age-id '<SENT_MESSAGE_ID>' --input /controlled-temporary-directory/atomic-issues.json --delete-input python3 scripts/auto_reply_permissions.py confirm --event-id '<EVENT_ID>' --int…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesreferences/onboarding.md:132 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file… and the number of historical evidence. 7. After the owner confirms the current write, write `user_memory.md` through the onboarding-only command below. This does not turn on ongoing Draft…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_runtime.py:668 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Authorization escalation languagereferences/storefront-discovery.md:3 · Authorization escalation language · informational: not an instruction file… merchant connectors; it never replaces order, customer, payment, inventory, or admin access. ## Run discovery Initialize the runtime first, then run from the Skill direc…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 filesreferences/learning-workflow.md:122 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileIf `memory.usage_enabled=false`, do not add a `user_memory.md` preference or playbook to the Draft-generation context; continue with the standard process.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/build_release_artifact.py:54 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif lower_name.endswith(SENSITIVE_SUFFIXES) or lower_name == ".env" or lower_name.startswith(".env."):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesscripts/configure.py:718 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileerrors.append("user_memory.md is missing its managed-memory markers")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_runtime.py:693 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_runtime.py:484 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesreferences/onboarding.md:231 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file5. Clearly tell users: past reply methods and later Draft-edit learning results are saved in the running version `user_memory.md`; view it read-only with:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_runtime.py:26 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_runtime.py:678 · Python subprocess execution detectedunconfirmed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionSKILL.md:133 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/auto_reply_permissions.py check --input /controlled-temporary-directory/atomic-issues.json --delete-inputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:127 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/user_memory.py merge --source onboarding --input /controlled-temporary-directory/memory-update.json --confirm-owner-request --delete-inputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/configure.py:254 · File type combined with upload action — agent may exfiltrate local data files…"Default sending mode: draft_only") print( "Next step: Review config.json, system-prompt.md, workflow.md, persona.md, user_memory.md, and auto_reply_permissions.json. Automatic sending stays disabled until the owner enables it and confirms…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
≈4,687 tok
1 file · 32 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

20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim ecom-agent-tools: 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. 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.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ecom-agent-toolsPropose a patch to the maintainer