soul-md-creator
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided
SOUL.mdandIDENTITY.mdfiles as context for drafting new persona definitions, which creates a surface where instructions embedded in those data files could influence agent behavior. - Ingestion points:
SKILL.mdrequires the agent to read existing personality files from the workspace to perform rewrites and alignments. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the ingested markdown content.
- Capability inventory: The skill is restricted to generating rationales and markdown text; it does not perform network operations, file-system writes (outside of user output), or shell command execution.
- Sanitization: No input validation or content filtering is specified for the files processed by the agent.
Audit Metadata