jsonlogic
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted business rules and data from the user and renders them in an interactive playground artifact, which is a potential surface for instructions hidden in data.
- Ingestion points: User-provided rules and sample data in chat conversations, processed in SKILL.md.
- Boundary markers: Absent; instructions do not specify using delimiters or warnings to prevent the agent from obeying instructions embedded within the logic rules.
- Capability inventory: Publishes interactive HTML artifacts using the Artifact tool and executes rules via scripts/jsonlogic.rb.
- Sanitization: Uses standard JSON.stringify for serialization but lacks explicit logic-level sanitization for the templated artifact.
- [EXTERNAL_DOWNLOADS]: The helper script scripts/jsonlogic.rb performs automated installation of the json-logic-rb gem from the RubyGems registry if it is not already present on the system. This is a standard dependency for the skill's primary execution functionality.
Audit Metadata