The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the Flare API, which includes exception messages, class names, stack traces, and code snippets from external applications. These data points serve as untrusted ingestion points for potential indirect prompt injection attacks.
Ingestion points: Data enters the agent's context through flare CLI commands such as list-project-errors and list-error-occurrences, as described in SKILL.md and workflows.md.
Boundary markers: The instructions do not define specific boundary markers or clear separators to distinguish untrusted external data from the skill's own instructions.
Capability inventory: The skill has the capability to execute shell commands via the flare CLI and is instructed to read local source files to assist in error debugging, as outlined in the workflows documentation.
Sanitization: There is no evidence of specific sanitization or filtering logic applied to the external content before it is presented to the agent.
[EXTERNAL_DOWNLOADS]: The skill guides the user to install the flare-cli tool using composer global require spatie/flare-cli. This is the official command-line tool provided by the vendor and is necessary for the skill to function.
[COMMAND_EXECUTION]: The skill operates by executing shell commands using the flare CLI. The provided workflows also suggest the use of git diff and local file reading commands to analyze and debug application errors.

flare