The Agent Skills Directory

[SAFE]: The skill fetches documentation from https://docs.avohq.io/3.0/llms-full.txt. This is the official documentation source for the Avo framework and is consistent with the skill's intended purpose.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard Rails generator commands (e.g., bin/rails generate avo:resource). These are expected and legitimate development actions.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves external data, creating a theoretical attack surface.
Ingestion points: WebFetch is used in SKILL.md to fetch documentation.
Boundary markers: The skill does not define specific delimiters for separating the fetched content from system instructions.
Capability inventory: The agent has access to Bash, Write, Edit, Read, Grep, and Glob tools.
Sanitization: No specific sanitization or filtering of the fetched content is described.
Note: This ingestion is considered safe because it targets a well-known official domain relevant to the skill's primary function.

avo-coder