breach
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill package is composed entirely of Markdown documentation and reference guides. It does not include any executable scripts, binaries, or functional code components.
- [PROMPT_INJECTION]: The skill contains strings such as 'Ignore all previous instructions' and 'DAN' within its AI red-teaming reference files. These are documented as test case examples for security professionals to use when assessing LLMs and do not attempt to override the current agent's instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze architectural descriptions and threat models provided by users. While this constitutes an ingestion point for untrusted data, the skill has no autonomous capabilities or custom tools that could be leveraged for exploitation.
- [NO_CODE]: The absence of scripts or executable logic in the repository minimizes the attack surface to purely informational content, posing no technical risk to the execution environment.
Audit Metadata