The Agent Skills Directory

[SAFE]: The skill uses a restricted set of tools (LSP, Read, Glob, Grep) to navigate and analyze local Rust source code. No dangerous tools like shell execution or file-write are requested.
[SAFE]: No network operations, external downloads, or remote code execution patterns were detected.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation attempts were found in the instructions or metadata.
[INDIRECT_PROMPT_INJECTION]: The skill reads external data (local source code files) via Read and Grep, which is a theoretical ingestion point for indirect prompt injection. However, because the skill lacks high-risk capabilities such as network access, file modification, or command execution, the impact is minimal.
Ingestion points: Local source code files via Read, Grep, and LSP tool outputs.
Boundary markers: Absent; instructions do not explicitly tell the agent to ignore embedded instructions in the code it reads.
Capability inventory: LSP navigation, Read, Glob, Grep. No tools for writing files, network access, or shell execution.
Sanitization: Absent; the skill does not specify escaping or filtering of read content.

rust-trait-explorer