The Agent Skills Directory

[SAFE]: The skill's primary function is to provide a structured workflow for refining documentation. It operates within the expected bounds of a technical analyst role without attempting to bypass safety filters or execute unauthorized commands.- [DATA_EXFILTRATION]: The skill requests access to a user-specified draft specification file. This behavior is transparently described in the documentation and is necessary for the skill's functionality. No evidence of data being sent to external or unauthorized domains was found.- [PROMPT_INJECTION]: The skill uses instructional language to define its persona and tasks. No malicious prompt injection patterns, such as instructions to ignore safety guidelines or reveal system prompts, were detected.- [COMMAND_EXECUTION]: While the skill includes instructions to save a generated summary to a file, this is a standard document management task and does not involve the execution of arbitrary shell commands or privilege escalation.- [REMOTE_CODE_EXECUTION]: There are no patterns indicating the download or execution of remote scripts. The skill relies entirely on the language model's reasoning capabilities and standard file-writing operations.

refine-specification