The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill's setup documentation in references/install-and-provider-setup.md includes a command to install the Fabric tool by piping a remote script from its GitHub repository directly into a shell (curl | bash).
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and process untrusted external data.
Ingestion points: Untrusted data is retrieved from stdin, local files, clipboard content, and transcripts as specified in SKILL.md and references/routing-and-mode-selection.md.
Boundary markers: There are no instructions or scaffolds that use delimiters or warnings to prevent the agent from executing instructions embedded within the processed text.
Capability inventory: The skill is granted access to the Bash, Read, and Write tools, which could be leveraged if the agent obeys instructions found in the ingested data.
Sanitization: The skill does not implement any validation or escaping mechanisms for the external content it processes.
[COMMAND_EXECUTION]: The skill is primarily centered around generating and executing shell commands using the Bash tool to interact with the Fabric CLI and its pattern library.
[EXTERNAL_DOWNLOADS]: The skill references and provides commands to download configuration and scripts from external sources, specifically the official repository for the Fabric tool.

fabric