kata-jido-testing
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process external project files like mix.exs and test helpers to generate appropriate test coverage. This creates a surface for indirect prompt injection if the analyzed files contain adversarial instructions intended to influence the agent's behavior during test generation. \n
- Ingestion points: Project files including mix.exs, active instructions, test helpers, and existing test suites (SKILL.md). \n
- Boundary markers: None specified to distinguish external code from instructions. \n
- Capability inventory: Shell execution capability is required to run the generated tests as per the instructions. \n
- Sanitization: No sanitization or validation of the ingested code content is mentioned. \n- [NO_CODE]: The skill consists exclusively of markdown instructions and metadata, with no accompanying scripts or executable binary files.
Audit Metadata