The Agent Skills Directory

[PROMPT_INJECTION]: No prompt injection or behavior override patterns were detected. The instructions strictly cover technical documentation for embedded Rust development.
[DATA_EXFILTRATION]: No sensitive file paths, credential access, or unauthorized network operations were identified. The network references are limited to official documentation sites (docs.rust-embedded.org, rtic.rs, embassy.dev).
[REMOTE_CODE_EXECUTION]: No remote script execution patterns (e.g., curl | bash) were found. The skill suggests standard local developer tools like probe-rs and cargo for flashing and debugging hardware.
[COMMAND_EXECUTION]: The skill mentions common development commands such as cargo run and rustup target add. These are standard operations for setting up a Rust embedded environment and do not involve unauthorized privilege escalation.
[OBFUSCATION]: No base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques were found in the instructions or code snippets.
[INDIRECT_PROMPT_INJECTION]: While the skill assists in processing user code, it does not demonstrate any unsafe interpolation of untrusted data into agent instructions. It follows standard programming assistance patterns.

rust-embedded