LinkedIn Poster
Analysis
This is a straightforward LinkedIn posting skill; it can publish public posts using a configured LinkedIn token, but that behavior is disclosed and the instructions require owner approval.
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.
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.
message send --channel linkedin --text "Your post content here"
The skill documents use of the message tool to publish to LinkedIn, which is a high-impact public posting action even though it is central to the skill's purpose.
Supported image sources: - Local file paths: `/Users/david/image.png` - `file://` URLs: `file:///Users/david/image.png` - Remote URLs: `https://example.com/image.png`
The skill can attach local or remote images to posts. This is purpose-aligned, but local media could unintentionally reveal private or sensitive content if not reviewed.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
`accessToken`: OAuth 2.0 token with `w_member_social` scope
The skill requires a LinkedIn OAuth token with permission to post on behalf of the user; this is expected for a posting skill but is sensitive delegated authority.
