writing-structure-planner
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted user-provided writing material to generate structural plans and diagrams.
- Ingestion points: User-provided text, research corpus, or existing drafts are processed in Step 1.1.
- Boundary markers: The instructions do not specify any delimiters (like xml tags or triple quotes) or 'ignore embedded instructions' warnings for the material being analyzed.
- Capability inventory: The skill has the capability to write to the local file system, creating analysis files like
writer-structure-material-analysis.mdandwriter-structure-options.mdbased on the user material. - Sanitization: There is no evidence of sanitization, validation, or filtering of the external content before it is interpolated into the analysis output or used to influence the structural suggestions.
Audit Metadata