quiz-generator
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from both local file paths and web searches without defining clear boundaries or instructing the agent to ignore potentially malicious embedded instructions.
- Ingestion points: Local files (SKILL.md, Step 1.2) and web content (SKILL.md, Step 1.3).
- Boundary markers: Absent; the skill does not use delimiters or specify that external content should be treated as data only.
- Capability inventory: The agent has access to
Read,WebSearch,WebFetch, andWritetools, creating a risk if malicious instructions trigger unauthorized file access or data creation. - Sanitization: Absent; no validation or filtering is applied to the content retrieved from external sources before it is processed for quiz generation.
Audit Metadata