Amazon Keyword Research
Analysis
The skill is mostly a prompt for Amazon keyword strategy, but it asks for unrestricted Bash access and references CLI/memory behavior without clear implementation or limits.
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.
allowed-tools: Bash
This grants the skill access to a broad local shell tool, while the artifact is otherwise an instruction-only Amazon keyword strategy prompt and does not scope or justify shell use.
kw research [keyword] # full keyword research from seed term
The skill documents a `kw` command interface, but the provided install information says there is no install spec and no required binary, leaving the origin or existence of that command unclear.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
kw save [name] # save keyword set to memory kw history # show saved keyword sets
The skill implies persistent saved keyword sets and history, which may contain product ideas, competitor ASINs, or marketing strategy, but does not describe retention or deletion controls.
