legiox-oath
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
jqutility for parsing JSON files. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data to update the architectural context, which creates a potential surface for indirect instructions from those data sources.
- Ingestion points: Data is ingested via the
legiox-knowledgeandlegiox-file-infotools as described in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for external content.
- Capability inventory: The skill enables command execution through the
jqutility. - Sanitization: There are no explicit instructions to sanitize or validate the content retrieved from external tools before context updates.
Audit Metadata