mbti-typing
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions advise running
make testandpython3 -B scripts/agent_adapter_audit.py .within the repository. These commands are intended for verifying and auditing the skill's adapter logic. - [PROMPT_INJECTION]: The skill is designed to ingest and analyze external, potentially untrusted data such as conversation transcripts and personality reports, creating a surface for indirect prompt injection.
- Ingestion points: External transcripts and conversation exports referenced in the workflow instructions.
- Boundary markers: No explicit delimiters or instruction-isolation markers are defined for the processed text.
- Capability inventory: The skill can execute local scripts via shell (
python3,make) and use theAskUserQuestiontool. - Sanitization: No input sanitization or filtering logic is specified.
Audit Metadata