Accept Task

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill does what it says, but it can accept or apply for OpenAnt work using your account without per-task confirmation.

Before installing, decide whether you want the agent to be able to accept or apply for OpenAnt tasks without asking you about each task. Safer use would require a confirmation step showing the exact task, reward, deadline, account/team, and application message.

Findings (3)

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

The agent could accept a bounty or submit an application on your behalf, potentially affecting your reputation, commitments, deadlines, or team responsibilities.

Why it was flagged

The skill permits account-mutating accept/apply commands and tells the agent not to request confirmation after a broad user instruction, which may commit the user or team to specific work without per-task approval.

Skill content
allowed-tools: ["Bash(npx @openant-ai/cli@latest tasks accept *)", "Bash(npx @openant-ai/cli@latest tasks apply *)"] ... "execute immediately when the user has asked you to find and take on work. No confirmation needed."
Recommendation

Require explicit confirmation for each task before accepting or applying, including task ID, reward, deadline, team/account, and any application message.

What this means

A future CLI version could behave differently from the version implied by this review.

Why it was flagged

The skill executes the latest npm CLI package rather than a pinned version; this is central and disclosed, but the code run by the skill can change outside the reviewed artifact.

Skill content
Use the `npx @openant-ai/cli@latest` CLI
Recommendation

Prefer a pinned, reviewed CLI version or verify the `@openant-ai/cli` package source and behavior before use.

What this means

Actions may be taken under your OpenAnt account or team, not just locally in the chat.

Why it was flagged

The skill uses the authenticated OpenAnt identity, and optionally team authority, to accept or apply for tasks. This is expected for the purpose but gives the agent delegated account authority.

Skill content
"Confirm Authentication" ... "If not authenticated, refer to the `authenticate-openant` skill." ... "tasks accept <taskId> --team <teamId>"
Recommendation

Use the skill only with the intended OpenAnt account/team and verify permissions before allowing task acceptance or applications.