story-memory
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow that ingests untrusted external data and uses it to modify project files.
- Ingestion points: The skill instructions in resources/fact-extraction.md and resources/story-context.md describe reading written chapters, scene drafts, and conversation history as primary inputs for knowledge extraction.
- Boundary markers: There are no explicit instructions or templates provided for using boundary markers or 'ignore embedded instructions' warnings when processing manuscript text.
- Capability inventory: The skill instructions describe capabilities for writing and updating files within the kb/, work/, and issues/ directories as seen in resources/writing-artifacts.md and resources/writing-issues.md.
- Sanitization: The skill lacks explicit sanitization or validation routines for text extracted from chapters before it is interpolated into wiki pages or fact entries.
Audit Metadata