engineering-ai-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files, creating a potential attack surface for indirect instructions.
- Ingestion points: The workflow processes
ai/memory-bank/requirements.md,ai/memory-bank/data-sources.md, and other files in theai/memory-bank/directory usingcatandgrepcommands. - Boundary markers: The instructions do not define delimiters or specific safety instructions (e.g., "ignore embedded instructions") for handling content from these files.
- Capability inventory: The agent is equipped with shell execution (
cat,ls,grep) and a wide range of machine learning, data processing, and API integration capabilities. - Sanitization: There is no explicit validation, filtering, or sanitization of the content read from the memory bank files before it is processed by the agent.
Audit Metadata