indexion-agent-orient
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve executing the
indexionCLI tool to generate orientation maps, render evidence-backed briefs, and perform semantic searches within the codebase. These commands are localized to the repository and used for their stated purpose of codebase analysis. - [PROMPT_INJECTION]: The workflow involves ingesting data from the local environment that could potentially contain indirect instructions.
- Ingestion points: The skill reads
task.md, task strings provided via the--taskflag, and repository content such as READMEs and wiki pages. - Boundary markers: No explicit delimiters are specified to isolate processed content from agent instructions.
- Capability inventory: The skill utilizes
indexionfor mapping and searching but does not inherently trigger dangerous system operations based on the ingested content. - Sanitization: The skill relies on the
indexiontool's internal logic for processing and does not specify manual sanitization steps for the input data.
Audit Metadata