wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of natural language instructions intended to improve communication between the user and the agent. It does not perform any automated tasks or background operations.
- [NO_CODE]: There are no executable scripts (.py, .js, .sh) or binaries included in the skill. The disable-model-invocation flag in the frontmatter explicitly prevents the model from calling tools during the execution of these instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read and incorporate content from local project files (GLOSSARY.md and GLOSSARY-MAP.md). * Ingestion points: GLOSSARY.md and GLOSSARY-MAP.md located in the repository. * Boundary markers: None specified in the prompt. * Capability inventory: None. The skill does not have access to tools, network, or file-writing capabilities due to the disable-model-invocation: true setting. * Sanitization: No specific sanitization or filtering is applied to the content of the glossary files.
Audit Metadata