The Agent Skills Directory

[COMMAND_EXECUTION]: The install.sh script automates the setup process by creating directories and copying files within the user's home directory. This is standard behavior for skill installation.
[EXTERNAL_DOWNLOADS]: The skill instructions include a 'Pattern Refresh Protocol' that fetches data from Wikipedia's public API. These requests target a well-known service to keep the skill's detection database updated with the latest community research.
[PROMPT_INJECTION]: As an editing tool, this skill processes untrusted user-provided text. It currently lacks explicit boundary delimiters or instructions for the agent to ignore commands embedded in that text, which is an inherent surface for indirect prompt injection.
Ingestion points: User-provided text for auditing (documented in SKILL.md).
Boundary markers: None identified; the skill directly interpolates user content into its workflow.
Capability inventory: The skill uses Read, Edit, and Write tools to modify text files.
Sanitization: None; the skill is designed to evaluate the writing style of the input as-is.
[REMOTE_CODE_EXECUTION]: Automated tools flagged a pattern where remote data from Wikipedia is piped to a local Python interpreter. Analysis confirms this is used solely for parsing JSON data from a trusted source using a static script, and it does not involve executing the remote content as code.

antislop