Security audit
Security checks for vulnerabilities and agentic risk
This is a plain Markdown guidance skill for reviewing Elixir documentation, with no executable code, persistence, credential handling, or hidden data movement.
Installers should treat this as low-risk documentation-review guidance. Be aware that following its optional verification flow may involve reading project source and running tests, and the separate review-verification-protocol dependency should be trusted before use.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
def permissions(:admin), do: [:read, :write, :delete] def permissions(:editor), do: [:read, :write] def permissions(:viewer), do: [:read]
Tips for Dialyzer compatibility:
The @doc text first says the function 'returns whether the request should proceed,' which implies a boolean result, but a few lines later says it returns {:ok, remaining} or {:error, :rate_limited}. Because this file is guidance for reviewing documentation quality, embedding a contradictory example directly conflicts with the stated instructional intent.
No suspicious patterns detected.