skills/holistics/skills/validate-aql/Gen Agent Trust Hub

validate-aql

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an interface for validating AQL queries which acts as an ingestion point for untrusted data.
  • Ingestion points: The aql parameter in the validate_aql tool (described in SKILL.md) is used to process user-provided or agent-generated query strings.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided within the skill's markdown body to isolate the query content.
  • Capability inventory: The skill utilizes the validate_aql tool, which performs validation checks against the Holistics platform (remote network operation).
  • Sanitization: There are no instructions for sanitizing or escaping the query content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 09:59 AM