The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the user to execute shell commands to install and run the resume generation tool.
Evidence: pip install rendercv, rendercv new "John Doe", and rendercv render cv.yaml commands are documented for the user in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data such as work experience, education history, and professional summaries which are then interpolated into CV templates. This creates a surface where embedded instructions in a user's resume data could potentially influence the agent's behavior during the rendering process.
Ingestion points: User-provided CV information in SKILL.md (YAML structure and example prompts).
Boundary markers: None identified; the skill does not explicitly instruct the agent to ignore instructions embedded within the user data.
Capability inventory: Shell command execution via rendercv and MCP tools for document manipulation (create_docx, docx_to_pdf).
Sanitization: None identified; the skill does not describe any validation or escaping of the user-provided content before processing.
[EXTERNAL_DOWNLOADS]: The skill references an external software repository and documentation for its core functionality.
Evidence: Provides links to github.com/sinaatalay/rendercv and docs.rendercv.com in the Resources section of SKILL.md.

cv-builder