senior-solution-architect
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands like
ls -Randgrepto perform automated discovery of the local file system, scanning for framework dependencies and infrastructure patterns in Phase 1 of the workflow. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and processes untrusted data from local repository files to inform its architectural design.
- Ingestion points: Phase 1 in
SKILL.mdreads file content frompackage.json,Dockerfile,terraform/,k8s/, and other configuration files. - Boundary markers: Absent. There are no delimiters or instructions to ignore embedded instructions within the files being read.
- Capability inventory: The skill uses the discovered data to generate C4 Mermaid diagrams and Architecture Decision Records (ADRs).
- Sanitization: Absent. The skill does not perform filtering or sanitization of the content extracted from the codebase before processing.
Audit Metadata