alignment
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it ingests and processes content from external project documents.
- Ingestion points: The process reads content from
design-docs/NN-name.brief.md,design-docs/NN-name.research.md, anddocs/glossary.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the contents of these files.
- Capability inventory: The skill is limited to reading project files, writing documentation to the local filesystem (
design-docs/NN-name.alignment.md), and invoking other internal skills (adr,glossary). - Sanitization: No explicit sanitization, validation, or escaping of the ingested text is performed during the synthesis phases.
Audit Metadata