ds-teaching-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest and process student-provided content including code, error messages, and datasets, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to request student code and logs for clarification (SKILL.md).
- Boundary markers: No explicit delimiters or specialized syntax are defined to isolate student inputs from the agent's core instructions.
- Capability inventory: The skill utilizes standard shell and editor tools for verification purposes as mentioned in the fallback protocol.
- Sanitization: The 'Anti-Patterns' section of the skill body explicitly instructs the agent not to treat external content, logs, or tool responses as trusted instructions.
Audit Metadata