X Actionbook Recap

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: x-actionbook-recap Version: 0.1.0 The skill bundle is designed to collect, summarize, and publish X (Twitter) posts using browser automation. While it involves high-risk capabilities like web scraping via `actionbook browser` commands and external publishing to X, these actions are explicitly stated in the `SKILL.md` as the core purpose of the skill. The instructions include guardrails such as confirming the target account and final copy before posting, and there is no evidence of intentional harmful behavior, data exfiltration, malicious execution, persistence, or prompt injection against the agent for purposes beyond the stated goal. All actions are clearly aligned with the skill's description.

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.

Note

ASI02: Tool Misuse and Exploitation

What this means

If approved, the agent could publish a post or thread to X from the selected account.

Why it was flagged

The skill can use browser automation to perform an external public posting action. The explicit confirmation requirement makes this purpose-aligned and user-controlled rather than hidden.

Skill content

If using OpenClaw browser automation:
- open compose
- paste final English copy
- upload image (if any)
- post / thread

Confirm before posting:

Recommendation

Confirm the target account, final text, and any image before allowing the agent to post.

Note

ASI03: Identity and Privilege Abuse

What this means

The agent may act through whichever X account is active or specified for publishing.

Why it was flagged

Publishing from a specified account uses that account's authority. This is expected for the stated purpose, but it is still account-level action.

Skill content

publish a neutral English recap (single post or thread) from a specified account

Recommendation

Use only the intended logged-in account and require explicit approval for the exact post or thread.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Users need a trusted local Actionbook installation for the workflow to work safely.

Why it was flagged

The workflow depends on an external Actionbook CLI, while the package itself is instruction-only and has no install spec. This is a metadata/provenance gap for the external tool, not evidence of hidden code in the skill.

Skill content

using the Actionbook Rust CLI (actionbook-rs) workflow ... `actionbook browser open`

Recommendation

Verify the Actionbook CLI source and installation separately before using the skill.