feedback-quality-analyser
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate educational analysis with no malicious intent detected. The instructions are clear, evidence-based, and focused on the stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input through fields like
feedback_textandtask_contextwhich are interpolated directly into the prompt. There are no explicit boundary markers or delimiters used to isolate this untrusted content from the system instructions. - Ingestion points:
SKILL.mdprompt section interpolates{{feedback_text}},{{task_context}}, and other user-controllable fields. - Boundary markers: Absent. The prompt relies on markdown formatting but lacks robust isolation markers for user data.
- Capability inventory: None. The skill generates text responses and does not invoke network operations, file system writes, or subprocess executions within the analyzed file.
- Sanitization: Absent. The input is processed as provided without filtering.
Audit Metadata