The Agent Skills Directory

[SAFE]: The skill provides procedural guidance for code analysis without including executable scripts or remote downloads.
[PROMPT_INJECTION]: The skill's core function of reviewing untrusted source code presents an inherent surface for indirect prompt injection.
Ingestion points: Source code files accessed via the Read tool as described in the review process.
Boundary markers: The instructions do not specify the use of delimiters to isolate untrusted code content from agent instructions.
Capability inventory: The skill has access to file reading tools (Read, Grep, Glob) and a shell (Bash).
Sanitization: No sanitization or filtering of the code content is performed before processing.

reviewing-code