Libraria
Analysis
The skill appears to be a legitimate Libraria integration, but it gives the agent broad authenticated ability to run Libraria actions, including deletion and raw API requests.
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.
When the available actions don't cover your use case, you can send requests directly to the Libraria API through Membrane's proxy... HTTP method (GET, POST, PUT, PATCH, DELETE).
The skill documents a broad authenticated API proxy, including mutating and deleting methods, without clear limits or explicit confirmation requirements.
npm install -g @membranehq/cli
The setup requires installing an unpinned global npm CLI package, while the registry metadata lists no install specification or required binary.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Membrane handles authentication and credentials refresh automatically... The user completes authentication in the browser.
The skill relies on delegated Membrane/Libraria authentication and ongoing credential refresh, which is expected for the integration but sensitive.
