fork-discipline
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses standard bash utilities (grep, find) and filesystem tools to perform architectural audits of multi-client codebases.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted codebase content to generate audit reports, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Codebase files scanned using Read, Grep, and Glob tools.
- Boundary markers: The skill does not define specific output delimiters or instructions to ignore embedded commands in the generated reports.
- Capability inventory: Bash, Write, Edit, Read, Glob, Grep tools are available to the skill.
- Sanitization: Content extracted from the codebase is not sanitized before being placed into the report artifact at .jez/artifacts/fork-discipline-audit.md.
Audit Metadata