setup-solid
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes repository contents to generate documentation, creating a surface for indirect prompt injection if source files are compromised. As this behavior is central to the skill's purpose of documenting architecture, it is considered a low-risk surface.
- Ingestion points: Reads CLAUDE.md, AGENTS.md, GLOSSARY.md, and Architecture Decision Records (ADRs) from .agents/adr/ or docs/adr/.
- Boundary markers: Absent. The skill does not specify delimiters or 'ignore embedded instructions' warnings for the ingested text.
- Capability inventory: The skill has file-write access to modify CLAUDE.md or AGENTS.md. No network or subprocess execution capabilities are present.
- Sanitization: Absent. The skill does not explicitly perform validation or filtering of the ingested architectural concepts before drafting the documentation section.
Audit Metadata