SlipBot Instapaper Importer
Analysis
This instruction-only skill appears benign: it parses pasted Instapaper exports and creates slipbox notes only after user confirmation.
Findings (2)
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.
Precheck → show user: article title, note count, ask for confirmation 4. On confirmation → for each note, invoke slipbot
The skill delegates note creation to slipbot after an explicit confirmation step; this is disclosed and central to the importer purpose.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Each user note becomes a separate slipbox entry
The imported text is persisted into the user's slipbox, which may be reused by later slipbox workflows; this persistence is expected for the skill.
