The Agent Skills Directory

[COMMAND_EXECUTION]: The skill employs rg (ripgrep) to inspect existing view and ruby files within the app/ directory. It also relies on the ability to execute rails commands through bin/rails and bundle exec rails. While these tools are essential for Rails development, they provide the agent with broad execution capabilities within the project context.\n- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze the project's existing forms and builders to ensure consistency. This ingestion of untrusted data from the local environment lacks specific security controls.\n
Ingestion points: The agent reads contents from app/views/ and app/ using Read and Grep tools.\n
Boundary markers: There are no instructions provided to the agent to treat existing code as untrusted or to ignore instructions embedded within comments in those files.\n
Capability inventory: The skill is granted Write, Edit, and Bash (Rails) permissions, which can be leveraged if the agent is influenced by malicious instructions in the code it reads.\n
Sanitization: The skill does not implement any validation or sanitization of the data retrieved from existing files before it is used to influence further actions.

form-helpers