The Agent Skills Directory

[SAFE]: The skill contains standard documentation and code snippets for Ruby on Rails development. No suspicious command execution, network activity, or obfuscation was detected.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to interact with and modify local project files using tools like Read, Write, Edit, and Bash.
Ingestion points: Ingests project source code through Read, Grep, and Glob tools.
Boundary markers: Relies on standard Markdown formatting; no explicit prompt-level delimiters or instructions to ignore embedded commands are present in the provided documentation.
Capability inventory: Includes the ability to write/edit files and execute shell commands via Bash, which could be abused if the agent processes malicious data from the project repository.
Sanitization: No specific sanitization or filtering of external file content is described in the skill instructions.

action-mailer-coder