The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized capabilities were detected in the skill's instructions. The skill operates purely as a data parsing utility within a local environment.
[PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection (Category 8) by processing untrusted text from images. • Ingestion points: User-provided screenshots passed via the screenshots context parameter. • Boundary markers: No delimiters or explicit instructions to treat extracted image text as untrusted data are provided. • Capability inventory: The skill is authorized to perform local file-write operations to the <work_dir>/.work/jd-pool/ directory. • Sanitization: Extracted text fields such as job_description are interpolated into Markdown templates without sanitization or escaping.

job-hunt-fetcher