The Agent Skills Directory

[SAFE]: The skill's instructions and metadata are consistent with its stated purpose of providing a read-only code audit for Elixir applications. No malicious instructions, obfuscation, or data exfiltration patterns were detected.
[COMMAND_EXECUTION]: The skill utilizes shell commands like grep to identify specific code patterns (e.g., list assignments, Ecto preloads) within local source files. This is a standard approach for static code analysis tools.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill ingests untrusted data by reading local Elixir and HEEX files which could contain malicious comments.
Ingestion points: File reading via Read and Grep tools on user-specified paths.
Boundary markers: None explicitly defined in the instructions for the data ingestion phase.
Capability inventory: The skill has access to Read, Grep, Glob, and Bash tools.
Sanitization: No explicit sanitization or filtering of the code content before processing.

assigns-audit