explain-architecture
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes repository content to generate architecture explanations, creating a surface for indirect prompt injection if the files being analyzed contain malicious instructions. \n
- Ingestion points: The instructions in SKILL.md direct the agent to read project guidance, architecture documents, implementation files, and tests. \n
- Boundary markers: The skill lacks explicit instructions to use boundary markers or to ignore instructions embedded within the analyzed data. \n
- Capability inventory: The skill primarily performs file reads but mentions that running project checks is optional. \n
- Sanitization: No sanitization or filtering of the ingested content is specified in the skill instructions.
Audit Metadata