aif-archive
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests content from project-managed plan files to determine task completion. While this presents an indirect prompt injection surface, the risk is minimal due to the specific task-parsing logic and restricted file-management actions. Ingestion points: Plan files in
.ai-factory/plans/andROADMAP.md. Boundary markers: Uses## Tasksheaders and specific checkbox patterns. Capability inventory: UsesBashformvandmkdir, andEditfor metadata updates. Sanitization: Employs strict matching for- [x]and- [ ]patterns. - [COMMAND_EXECUTION]: Employs Bash for
mv,mkdir, andgit logoperations. These tools are used appropriately for local archiving and version history retrieval within the project sandbox.
Audit Metadata