kata-jido-action
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute standard Elixir development tools, specifically
mix testandmix compile, to verify the correct implementation of actions within the project environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze local project files, such as
mix.exs, Elixir source files, and test files, to understand the current repository state and API. - Ingestion points: Reads project configuration (
mix.exs), existing actions, and their corresponding tests as described in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or specific security warnings to the agent when processing these files.
- Capability inventory: The skill has the capability to execute shell commands via the Elixir
mixtool (documented in SKILL.md). - Sanitization: No explicit sanitization, validation, or filtering of the content from ingested project files is mentioned.
Audit Metadata