architect
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external documentation, such as Product Requirement Documents (PRDs) and architecture specifications, to perform validation and documentation tasks. These external sources could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The
architect-checklist.mdinstructs the agent to locate and read several external files, includingarchitecture.md,prd.*.md, andfrontend-architecture.md. - Boundary markers: There are no explicit instructions or delimiters defined to treat the content of these external files as untrusted data or to ignore any embedded agent instructions.
- Capability inventory: The skill references tools for analyzing existing codebases (
document-existing-project) and creating architecture documentation, which involve extensive file system reads. - Sanitization: No sanitization or validation logic is present to filter out potential prompt injection patterns within the ingested documentation.
Audit Metadata