wtf
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from the previous LLM response and local project files (e.g.,
GLOSSARY.md,CONTEXT.md), which constitutes an indirect prompt injection attack surface. - Ingestion points: The skill reads the 'immediately previous LLM response' and searches for files matching
CONTEXT.md,GLOSSARY.md,UBIQUITOUS_LANGUAGE.md, and*.glossary.ymlwithin the project. - Boundary markers: The instructions do not define explicit boundary markers or delimiters for the ingested data.
- Capability inventory: The skill has no active capabilities; it is configured with
disable-model-invocation: true, preventing the agent from calling additional tools or executing code. - Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is processed for re-explanation.
Audit Metadata