The Agent Skills Directory

[SAFE]: The skill's primary functionality is limited to reading source code and providing architectural and stylistic feedback based on included reference documentation.
[PROMPT_INJECTION]: Potential surface for indirect prompt injection. The skill is designed to ingest and process untrusted external data in the form of Swift code and pull request diffs.
Ingestion points: The skill utilizes gh pr diff and git diff within SKILL.md to bring external code into the agent's context.
Boundary markers: The instructions do not explicitly define delimiters to separate the review instructions from the code being analyzed.
Capability inventory: The skill utilizes shell commands (git, gh) and file system access to perform its tasks.
Sanitization: No sanitization of the ingested code content is performed.
Note: This is an inherent risk for any code review agent and is considered a baseline risk rather than a malicious finding.

swift-review