Clinkding - Linkding Bookmark Integration

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

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.

What this means

If invoked incorrectly, the agent could delete bookmarks or other Linkding records the user intended to keep.

Why it was flagged

The skill documents commands that can permanently delete bookmark data. This is aligned with bookmark management, but it is a high-impact action users should review before approving.

Skill content
# Delete permanently
clinkding bookmarks delete 42
Recommendation

Confirm bookmark IDs and intended changes before allowing delete, archive, update, upload, or bundle/tag modification commands.

What this means

Anyone or anything with access to the configured token may be able to read or modify the user's Linkding bookmarks depending on that token's permissions.

Why it was flagged

The skill requires a Linkding API token for account access. This is expected for the integration, but the token grants delegated access to the user's Linkding data.

Skill content
clinkding config set token YOUR_API_TOKEN
Recommendation

Use a dedicated, least-privilege Linkding token if available, store it securely, and rotate it if it may have been exposed.

What this means

A future upstream package change could alter the behavior of the installed CLI compared with the instructions reviewed here.

Why it was flagged

The Go install path uses @latest, which means the installed code can change over time. This is a common CLI install pattern, but it is not pinned to a specific reviewed version.

Skill content
go | module: github.com/daveonkels/clinkding@latest
Recommendation

Install from a trusted upstream source and consider pinning to a known version if reproducibility is important.

What this means

Search results or bookmark details may expose personal or sensitive URLs, notes, tags, and reading history to the agent session.

Why it was flagged

The skill retrieves personal bookmark titles, descriptions, and tags into the agent workflow. This is central to the purpose, but bookmark metadata can reveal private interests or work context.

Skill content
Searchable library - Full-text search across titles, descriptions, tags
Recommendation

Avoid asking the agent to retrieve sensitive bookmark collections unless you are comfortable with that information appearing in the conversation context.