The Agent Skills Directory

[SAFE]: The skill instructions are focused on providing a code review service and do not contain any malicious patterns such as prompt injection, data exfiltration, or obfuscation. All provided code snippets are benign examples used for educational purposes.
[PROMPT_INJECTION]: Analysis of the indirect prompt injection surface:
Ingestion points: The skill is configured to use Read, Grep, and Glob tools to ingest untrusted source code from the project environment as part of its primary review task.
Boundary markers: There are no specific delimiters or "ignore" instructions provided to the agent to distinguish between its own operational instructions and content within the code files it analyzes.
Capability inventory: The skill has access to the Bash tool in addition to file-reading and search tools.
Sanitization: No sanitization or validation of the ingested code is specified in the instructions.
Context: While the surface for indirect injection exists, the instructions are strictly focused on analysis and reporting rather than taking automated actions on the code, minimizing the risk of exploitation.

simplicity-reviewer