tutor
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external course materials, including
notes.htmlandtask.md, to establish the scope of evaluations. This creates a surface for indirect prompt injection where malicious instructions embedded in these files could influence the agent's behavior. \n - Ingestion points: The agent is directed to read
notes.html,task.md,unit.md,AGENTS.md, andLearner.mdas primary context sources. \n - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the data files. \n
- Capability inventory: The skill is restricted to reading and writing local files (specifically markdown reports); it does not define network access or arbitrary code execution capabilities. \n
- Sanitization: There is no mention of filtering, escaping, or sanitizing the content ingested from the course workspace. \n- [NO_CODE]: The skill consists entirely of instructional markdown and configuration files, containing no executable scripts such as Python, JavaScript, or Shell scripts.
Audit Metadata