The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes documentation changes and public-facing text, which presents a surface for indirect prompt injection attacks.
Ingestion points: The skill analyzes changed documentation, examples, and strings as specified in the Review Flow of SKILL.md.
Boundary markers: The instructions lack explicit boundary markers or warnings to disregard instructions found within the reviewed data.
Capability inventory: The skill specifies the execution of local scripts via the just docs command in SKILL.md.
Sanitization: There is no indication of sanitization or filtering of the input documentation before it is processed by the agent.
[COMMAND_EXECUTION]: The skill directs the agent to execute specific shell scripts to manage documentation builds.
Evidence: SKILL.md contains instructions to run just docs, which triggers scripts/generate_api_docs.sh and scripts/docs/generate_rust_library_reference.py. These are standard developer tools for the documentation workflow of the repository.

review-doc-style