The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and does not include any executable scripts, shell commands, or binary files.
[PROMPT_INJECTION]: The instructions do not contain any patterns attempting to override system prompts, bypass safety filters, or extract underlying model instructions.
[DATA_EXFILTRATION]: No network calls (e.g., curl, wget, fetch) or sensitive file path access (e.g., .ssh, .aws) were identified. All data processing remains within the model's text generation context.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or packages. The links provided in the documentation are for informational reading on the productcompass.pm domain.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests external data ($RESUME and $JOB_POSTING), it lacks any 'capabilities' such as file-writing or command execution that could be exploited by an injection attack. The risk is limited to the text response generated for the user.

review-resume