The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external Rust source files, which constitutes a vulnerability surface for indirect prompt injection attacks.
Ingestion points: The skill reads source files using the Read tool as part of the refactoring process described in SKILL.md.
Boundary markers: There are no instructions providing delimiters or warnings to ignore malicious content embedded in the code comments or strings of the input files.
Capability inventory: The skill has the Edit tool, allowing it to modify the filesystem by writing back refactored code.
Sanitization: No sanitization or validation mechanisms are specified for the ingested content.
[COMMAND_EXECUTION]: The instructions direct the agent to run local development commands to verify code changes.
Evidence: Use of cargo fmt, cargo clippy, and cargo test in the verification section to ensure no regressions were introduced during simplification.
[SAFE]: The skill's primary logic follows established Rust best practices and project-specific safety constraints, such as preserving regex definitions and error context propagation.

code-simplifier