results-report
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external experiment analysis files to generate reports, creating a surface for indirect prompt injection where instructions embedded in analysis data could influence the agent's output.\n
- Ingestion points: The skill reads
analysis-report.md,stats-appendix.md, andfigure-catalog.md(referenced inSKILL.md) as source artifacts.\n - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the ingested analysis data.\n
- Capability inventory: The skill is capable of writing and updating markdown files in the
Results/Reports/directory, updating the.claude/project-memory/project memory file, and appending entries to Obsidian daily notes.\n - Sanitization: No validation, filtering, or escaping is performed on the content ingested from the analysis bundle before it is interpolated into reports or project state.
Audit Metadata