asb-carol-dealbreakers
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external files which creates a surface for indirect prompt injection.
- Ingestion points: The skill reads 'STRENGTHS-WEAKNESSES.md' and 'KEYSTONES.md' during Phase A (SKILL.md).
- Boundary markers: No explicit delimiters are used to separate file content from the agent's instructions.
- Capability inventory: The skill has permissions to read and write markdown files in the local project directory.
- Sanitization: The process requires user approval for proposed edits before any changes are written to disk.
Audit Metadata