The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run the agent-browser CLI for opening URLs and extracting text from web pages.
[EXTERNAL_DOWNLOADS]: The skill fetches data from well-known and official Rust community sources, including lib.rs, crates.io, docs.rs, releases.rs, rust-lang.org, and github.io. These operations are consistent with the skill's primary function of providing Rust-related information.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process content from external websites, which introduces a potential surface for indirect prompt injection if those sources contain malicious instructions.
Ingestion points: The skill reads text content from various external Rust documentation sites and repository registries (SKILL.md).
Boundary markers: There are no explicit instructions for the agent to use boundary markers or to ignore potential instructions embedded within the fetched external content.
Capability inventory: The agent has access to Bash (command execution), Task (subagent orchestration), and Read/Glob (file system operations).
Sanitization: The instructions do not specify any sanitization or filtering logic for the data retrieved from external web sources.

rust-learner