The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill scans repository files that may contain untrusted instructions.
Ingestion points: Step 1: Repo Scan extracts information from resume.*, cv.*, *.md, *.txt, *.tex, and *.rst files.
Boundary markers: The instructions do not prescribe the use of delimiters when processing external content.
Capability inventory: The agent has the ability to read and write to the filesystem and execute specific shell commands.
Sanitization: The skill does not define a process for sanitizing or escaping the data extracted from the repository.
[COMMAND_EXECUTION]: The skill uses discovery and verification commands.
Evidence: Performs environment checks using which pandoc.
Evidence: Verifies generated PDF output using `pdftotext cv.pdf
| head -80`.

cv-builder