validate-story-draft
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill treats the content of local markdown files in
.aiox-core/development/tasks/as the 'Source of Truth' for its operational logic. This creates an indirect prompt injection surface where the agent's behavior could be altered by modifying these external files. - [PROMPT_INJECTION]: Indirect prompt injection evidence chain:
- Ingestion points: The agent reads and follows instructions from
.aiox-core/development/tasks/validate-next-story.mdand.aiox-core/development/tasks/dev-validate-next-story.md. - Boundary markers: Absent. There are no delimiters or instructions to treat the loaded task file content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill has permissions to read the file system and update story files (write). It also features an autonomous 'yolo' mode which reduces user oversight.
- Sanitization: Absent. No validation, escaping, or filtering of the loaded markdown task content is performed before execution.
Audit Metadata