The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and refactor external Rust source code, which creates a potential surface for indirect prompt injection attacks where malicious comments or code patterns could influence agent behavior.
Ingestion points: The skill uses Read, Grep, and Glob tools to access and process the contents of local Rust files.
Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted code content from the agent's system instructions.
Capability inventory: The skill possesses the Edit capability, allowing it to modify files based on its analysis, and suggests the execution of shell commands like cargo test and grep for verification.
Sanitization: The instructions do not specify any validation or sanitization logic to strip potential injection attempts from the processed source code.

code-simplifier