v1.0.0

Moltbook Daily Digest (中文版)

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 5:25 AM.

Analysis

The skill mostly does what it says—fetches Moltbook posts and translates summaries—but it uses a Moltbook API key, an unpinned translation dependency, and an external translation provider.

GuidanceThis appears safe for its stated purpose if you intend to fetch Moltbook digests. Before installing, use the least-privileged Moltbook API key available, be aware that translation goes through Google Translate, and consider pinning the deep-translator dependency.

Findings (4)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceHighStatusNote

SKILL.md

pip3 install deep-translator

The setup uses an unpinned PyPI dependency. This is purpose-aligned for translation, but there is no version pin or install specification in the provided metadata.

User impactDependency behavior could change over time if a different package version is installed.

RecommendationInstall from a trusted environment and pin or review the deep-translator package version if reproducibility matters.

Tool Misuse and Exploitation

SeverityLowConfidenceHighStatusNote

references/api.md

POST /posts ... POST /posts/{post_id}/comments

The reference file documents public write actions even though the digest script only fetches posts. This is not evidence of automatic posting, but it is broader API capability documentation than the stated read-only digest purpose needs.

User impactIf an agent used the broader reference instead of the digest script, it could attempt account-mutating Moltbook actions.

RecommendationUse a read-only API key if possible and keep agent instructions limited to fetching and summarizing posts.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

scripts/digest.py

creds_file = os.path.expanduser("~/.config/moltbook/credentials.json") ... return data.get("api_key")

The script can read a local Moltbook API key when the environment variable is absent. This is needed for Moltbook API access and is disclosed in SKILL.md, but it is still account credential access.

User impactUsing the skill may give it access to your Moltbook API key.

RecommendationUse a least-privilege or read-only Moltbook key if available, and confirm the credentials file contains only the intended key.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

scripts/digest.py

to_chinese = GoogleTranslator(source='auto', target='zh-CN') ... zh_summary = to_chinese.translate(summary_text)

The script sends selected Moltbook post text to Google Translate via the translator library. This is disclosed by the skill description and fits the purpose, but it is an external provider data flow.

User impactContent being summarized may be shared with Google Translate for translation.

RecommendationAvoid using the skill for non-public or sensitive Moltbook content unless you are comfortable with that external translation flow.