Raindrop.io Bookmark Manager
Analysis
The skill mostly matches a Raindrop bookmark manager, but it needs review because the artifacts flag an apparent hardcoded OAuth secret despite saying secrets are not embedded.
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.
without exposing secrets inside the published skill ... never hardcode real client ids, secrets, access tokens, or refresh tokens into the skill
The documentation makes strong no-embedded-secret claims, but the static scan reports an apparent hardcoded client_secret in the published script.
`create-collection`, `update-collection`, and `delete-collection` ... `add-bookmark`, `update-bookmark`, and `delete-bookmark` ... `import-bookmarks` and `export-bookmarks`
The skill exposes commands that can create, update, delete, import, and export Raindrop account data. These actions are disclosed and purpose-aligned, but they are account-mutating operations.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
client_secret = [REDACTED] or creds.get("client_secret")The provided static scan flags this line as an exposed hardcoded API secret or token. If the redacted value is a real OAuth client secret, the published skill expands the credential boundary beyond user-supplied environment credentials.
