Publish-Mate
Analysis
Publish-Mate appears purpose-aligned, but it should be reviewed carefully because it can use WordPress credentials to automatically publish public posts, upload images, and create categories or tags.
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.
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.
`/auto-publisher` or `/auto-publisher publish` — Full pipeline: fetch → compose → upload images → publish ... Categories and tags are auto-created if they don't exist
The skill directs the agent to run a full pipeline that creates CMS posts, uploads images, and mutates categories/tags. That is purpose-aligned, but it is high-impact public publishing authority and the publish path does not require a final human content review.
Source: unknown; Homepage: none; Install specifications: [0] uv
The package provenance is not identified in the registry metadata, while the skill is intended to run code and handle CMS credentials. This is not evidence of malicious behavior, but it is worth verifying before granting access.
"schedule": {
"enabled": true,
"cron": "0 9 * * *",
"timezone": "Asia/Shanghai"
}The setup script writes an enabled daily schedule into the generated configuration, which is notable for an auto-publishing workflow even though it is disclosed and purpose-aligned.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
password_env = config["platform"].get("app_password_env", "WP_APP_PASSWORD") ... self.password = os.environ.get(password_env) ... "Authorization": self.auth_headerThe publisher loads a WordPress Application Password from the environment and sends it as the authorization credential for WordPress REST API actions.