The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands and various project-specific build/test tools such as golangci-lint, go build, npm run build, ruff, and pytest. While these are necessary for the skill's primary function of code review and quality assurance, they involve executing code and configurations defined within the codebase under review.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted source code and diffs. Maliciously crafted comments or code patterns in the reviewed files could attempt to manipulate the agent's behavior during the review process.
Ingestion points: The skill reads file content using git diff and the Read tool as specified in Workflow steps 1 and 3 of SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when processing the code content.
Capability inventory: The agent has access to powerful tools including Bash, Edit, Read, Grep, and Glob across all operations.
Sanitization: There is no evidence of input sanitization or filtering of the code content before it is processed by the model.

code-review