The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to run ./scripts/sync_to_docs.sh while passing the user-provided $ARGUMENTS directly to the shell. This creates a risk for command injection if the input includes shell metacharacters (such as ;, &, |, or backticks) which could be used to execute arbitrary commands on the host system.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from .qmd files and rendered HTML outputs, which could contain malicious instructions intended to influence the agent's behavior during the verification steps.
Ingestion points: Quarto source files (.qmd) in the Quarto/ directory and rendered HTML files in docs/slides/.
Boundary markers: No delimiters or safety instructions are used to separate the external content from the agent's internal instructions.
Capability inventory: The skill has access to the Bash tool, enabling file system manipulation, script execution, and potentially network access depending on the environment.
Sanitization: There is no evidence of sanitization or validation performed on the input files or the generated output before the agent performs verification tasks like grep or visually confirming content.

deploy