The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/cv.py utilizes subprocess.run to execute tectonic for LaTeX compilation and pdftoppm for generating review images from PDFs. These executions are performed securely using argument lists rather than shell strings, which effectively mitigates command injection risks.
[PROMPT_INJECTION]: The skill's workflow involves reading and processing job descriptions from external sources, which introduces a surface for indirect prompt injection. A malicious job description could attempt to override agent behavior. However, the skill explicitly requires visual review of the compiled artifacts and mandates human intervention before any final submission, providing significant mitigation against automated execution of injected instructions.

cv-creator