anfra-aql
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents the use of AI functions such as
ai_summarize,ai_complete, andai_classifythat process potentially untrusted data fields (e.g.,reviews.contentinreferences/examples/56.md). This creates a vulnerability surface where malicious instructions embedded in the data could influence the behavior of the AI models processing the AQL queries. - Ingestion points:
reviews.content(documented inreferences/examples/56.md) and other text fields passed to AI functions described inreferences/aql/ai-functions.md. - Boundary markers: The AQL language documentation does not specify boundary markers or sanitization requirements for text data processed by AI functions.
- Capability inventory: The skill provides knowledge on executing AQL, which includes powerful data transformation and AI-driven summarization, classification, and completion capabilities.
- Sanitization: No sanitization or escaping of external content is documented for the AI functions.
Audit Metadata