The Agent Skills Directory

[SAFE]: The skill contains no executable code, network operations, or sensitive file access. It consists entirely of natural language instructions guiding the agent to perform resume reviews.
[SAFE]: No prompt injection or behavior override patterns were detected. The instructional tone, while aggressive ('relentless', 'tear apart'), is contextually appropriate for its stated purpose of 'grilling' resume bullets and does not target safety filters.
[SAFE]: Indirect prompt injection risks are minimal. While the skill processes user-provided data (resumes), it does not possess capabilities (like file writing or network access) that could be exploited via malicious input.

grill-resume