codebase-design
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process external data including project instructions, architecture decisions, and existing code tests. \n
- Ingestion points: Workflow steps defined in SKILL.md and references/design-it-twice.md. \n
- Boundary markers: Absent; there are no instructions for the agent to use delimiters or specific ignore-tags for the ingested content. \n
- Capability inventory: None. This is an instructional skill and does not include scripts, subprocess calls, or network-active tools. \n
- Sanitization: Absent.\n- [EXTERNAL_DOWNLOADS]: The skill contains informational links to a GitHub repository (github.com/mattpocock/skills) for attribution and license compliance purposes in SKILL.md, LICENSE, and references/source-notes.md. These are documentation references and do not involve automated execution of remote code.
Audit Metadata