botlearn-writer
Analysis
This is a coherent instruction-only article-writing skill with no evidence of hidden code execution, credential use, persistence, or destructive behavior.
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.
"dependencies": { "@botlearn/summarizer": "workspace:*", "@botlearn/keyword-extractor": "workspace:*" }The skill depends on separate helper packages. This is disclosed and matches the article-writing purpose, but installation/use is not fully self-contained.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Use @botlearn/summarizer to condense research material into key points ... Use @botlearn/keyword-extractor to identify core terms
The agent is instructed to pass article topics or provided research material to declared helper skills. This is expected for the writing workflow, but it matters if the user provides confidential references.