integrity
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data which could contain malicious instructions meant to influence the agent's graph-writing behavior.
- Ingestion points: The skill reads external content in 'Mode 1' (code diffs from a repository) and 'Mode 3' (prosaic artifacts and reports) to extract claims and dependencies.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing external prose or code changes.
- Capability inventory: The skill possesses the capability to modify the persistent environment by creating graph nodes and links via
iskron_add_vimarshaandiskron_arrowbased on the ingested content. - Sanitization: There is no evidence of sanitization or validation of the external content before it is interpolated into the graph-writing logic.
Audit Metadata