Acp Job Submitter

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

An agent following this skill could submit paid or high-impact jobs beyond what the user expected, especially if the request involves crypto services.

Why it was flagged

The skill gives a broad job-submission interface to arbitrary third-party ACP agents with arbitrary requirements, but does not define approval, spend, service, or safety boundaries.

Skill content
Submit a job to any ACP agent ... submit_job <agent_wallet> <offering> <requirements_json>
Recommendation

Require explicit user confirmation before each job, restrict allowed agents and services, set a maximum USDC spend, and require separate confirmation for swaps, perpetuals, or other financial actions.

ConcernMedium Confidence
ASI03: Identity and Privilege Abuse
What this means

The user may not know which account pays for jobs, whether funds can be spent automatically, or who receives markup fees.

Why it was flagged

The documented workflow involves paid USDC job submission and markup, which likely requires wallet, account, or payment authority, but the artifacts do not clarify what identity or funds are used.

Skill content
Price | 0.25 USDC ... Job Submission (基本) | 0.1 USDC ... 賺取差價
Recommendation

Declare the required ACP wallet/account permissions, make the payer and fee recipient explicit, and require user approval before any charge or delegated account action.

What this means

The command may fail or may depend on code outside the reviewed artifact set.

Why it was flagged

The documentation references a local TypeScript helper and npx/tsx execution, but the provided package contains only SKILL.md, so the implementation and dependency provenance are not reviewable here.

Skill content
await exec("npx tsx bin/acp.ts job create ...")
Recommendation

Provide the referenced helper code and install specification, or clearly state that these are examples requiring a separately reviewed ACP CLI.

What this means

If followed, the skill may run local commands or external tooling in the user's environment.

Why it was flagged

The examples use shell execution through exec/npx. Command execution is related to the stated purpose, but users should notice that the skill is not purely informational.

Skill content
await exec("npx tsx bin/acp.ts job status 123456789")
Recommendation

Run commands only after reviewing the referenced CLI/script and avoid automatic command execution for paid or financial workflows.

What this means

Information included in job requirements may be shared with external agents or marketplaces.

Why it was flagged

The core workflow sends job requirements to third-party ACP agents. This is purpose-aligned, but the artifacts do not describe data handling or trust boundaries for those agents.

Skill content
Submit Job to Other Agents ... Browse ACP marketplace for agents
Recommendation

Do not include private keys, credentials, or sensitive personal/business data in job requirements, and verify the destination agent before submission.