wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses external files
GLOSSARY.mdandGLOSSARY-MAP.mdto define terminology, which creates a surface for indirect instructions to be processed by the agent. - Ingestion points: The agent is instructed to read
GLOSSARY.mdandGLOSSARY-MAP.mdinSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore any potential commands embedded within the glossary files.
- Capability inventory: The skill has no executable scripts and uses
disable-model-invocation: true, which significantly limits the agent's ability to perform actions or call tools based on ingested content. - Sanitization: No sanitization or filtering of the glossary content is specified.
Audit Metadata