vow-enforcement
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation demonstrates the use of shell pipes to execute local Python scripts (e.g.,
python plugins/imbue/validators/iron_law.py) as part of a validation protocol. These scripts act as quality gates within the 'Nen Court' enforcement layer to audit agent output and project history. - [PROMPT_INJECTION]: The skill's 'Nen Court' protocol creates a potential surface for indirect prompt injection by processing untrusted data during audits.
- Ingestion points: Validator scripts are designed to process agent-generated text, git logs, and file diffs as described in the Nen Court Protocol section of SKILL.md.
- Boundary markers: The provided documentation does not specify the use of delimiters or instructions for the validator agents to ignore potential injection content within the audited data.
- Capability inventory: The orchestrator relies on these Python-based validators to approve or block transitions between development phases.
- Sanitization: No input sanitization or validation of the ingested text is mentioned in the methodology.
Audit Metadata