style-extract
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted text provided by users to extract writing style dimensions.
- Ingestion points: Raw article text provided by the user for style extraction in 'Mode A'.
- Boundary markers: The instructions do not define specific delimiters or 'ignore' instructions for the source text.
- Capability inventory: The skill has the ability to read and write files within the
./writing-workspace/styles/directory. - Sanitization: The skill includes explicit instructions to correctly escape special characters (quotes, backslashes, and newlines) when writing to JSON files to prevent data corruption.
Audit Metadata