asb-carol-define
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from four local markdown files (STRENGTHS-WEAKNESSES.md, KEYSTONES.md, DEALBREAKERS.md, INCITING-EVENTS.md) to generate its output, creating an indirect prompt injection attack surface.
- Ingestion points: The skill reads working markdown files located in the current directory.
- Boundary markers: Instructions do not define specific delimiters or instructions to ignore commands that may be embedded in the ingested files.
- Capability inventory: The agent uses file system read and write capabilities to process inputs and generate the final CAROL.md file.
- Sanitization: No validation or filtering mechanisms are specified for the content retrieved from the local files before processing.
Audit Metadata