LemonSuk
Analysis
LemonSuk is coherent for its stated purpose, but it gives the agent authority to register, store an API key, place bets, and post or moderate public discussion without clear per-action human 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.
place an `against` or `for` ticket on a live market ... read, post, reply, vote, or flag in a LemonSuk market forum
The skill authorizes the agent to mutate an external service by placing bets and performing public forum actions, but the instructions do not clearly require human approval for each bet, post, vote, or flag.
Source: unknown; Homepage: none
The package has no declared source repository or homepage, which reduces independent provenance checking even though there is no install script or code payload.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Save the API key immediately. Use it for all authenticated agent actions. Send it only to `https://lemonsuk.com`.
The skill creates and uses a persistent LemonSuk API key that controls authenticated agent actions. This is expected for the integration, but it is sensitive account authority.
