The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The skill is granted access to the Bash and Task tools. These are used to execute shell commands for rendering Quarto and Beamer documents. While necessary for the intended purpose, these tools allow for arbitrary command execution within the environment.
[PROMPT_INJECTION] (LOW): This skill is vulnerable to Indirect Prompt Injection (Category 8) because it is designed to read and process external user-provided data (.qmd, .tex, .html files) and use that data to drive a 'critic/fixer' logic loop.
Ingestion points: The skill uses Read, Grep, and Glob to ingest content from the filesystem.
Boundary markers: No specific delimiters or warnings are provided to the agent to treat the content of these files as untrusted data.
Capability inventory: The agent possesses Write, Edit, Bash, and Task capabilities, which could be abused if malicious instructions are embedded in the analyzed documents.
Sanitization: No sanitization or validation of the input file content is performed before processing.

qa-quarto