Tweet Processor
Analysis
The skill is coherent and purpose-aligned: it processes user-provided tweet links and appends structured summaries to local note files.
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.
When user sends a tweet URL, automatically: 1. Navigate to the tweet ... 3. Categorize into tweet-notes/ files 4. Append with proper formatting
The skill directs the agent to use browser/navigation capability and make local file changes. This is disclosed and purpose-aligned, but users should know it will act automatically after receiving a tweet URL.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Appends to: - `tweet-notes/tools.md` ... - `tweet-notes/misc.md`
The skill persists summaries of external tweet content into local notes. This is the intended behavior, but external content can be inaccurate, misleading, or later over-trusted if reused.
