The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a specialized command-line utility named wewrite to perform various editorial functions. These include retrieving task information (wewrite run show), listing claims (wewrite sources list), scoring article quality (wewrite score), evaluating content (wewrite content-eval), and updating task metadata (wewrite run update).- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading and processing untrusted article drafts.
Ingestion points: The agent is instructed to read content from artifacts.draft and associated reference files located in the project directory.
Boundary markers: The instructions lack explicit delimiters or instructions to treat ingested content as data rather than instructions, which could lead to the agent following directives embedded within the articles it reviews.
Capability inventory: The skill has access to powerful tools including Bash for command execution and Write/Edit for modifying local files.
Sanitization: No specific sanitization or filtering logic is provided to handle potentially malicious content within the draft articles before they are processed by the agent or passed to the wewrite CLI.

wewrite-review