The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides installation instructions that use piped execution to bash and PowerShell (curl -fsSL https://d.officecli.ai/install.sh | bash and irm https://d.officecli.ai/install.ps1 | iex). This allows for arbitrary code execution on the host system from a remote, unverified source without auditing the script contents.
[COMMAND_EXECUTION]: The skill relies on executing the officecli tool via shell commands. It frequently interpolates user-controlled data such as file paths and property values into these commands, which could lead to command injection if the agent does not properly escape inputs.
[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8):
Ingestion points: Untrusted data enters the context through officecli view <file>, officecli get <file>, and officecli query <file> commands which read content from external Office documents.
Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore instructions embedded within the processed document content.
Capability inventory: The skill has access to shell execution (bash, officecli) and file system operations.
Sanitization: There is no mention of sanitization, validation, or filtering of the content extracted from documents before it is processed by the agent.

officecli