bmad-os-editorial-review-translation
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted content provided via the 'content' parameter. This presents an indirect prompt injection attack surface where a malicious translation could attempt to influence the agent's behavior. \n- Ingestion points: The 'content' input in SKILL.md handles untrusted translated text and PR diffs. \n- Boundary markers: The instructions lack explicit boundary markers or instructions to ignore instructions embedded within the translated content. \n- Capability inventory: The skill is limited to analysis and reporting; no subprocess calls, network operations, or file-writing capabilities are included in the instructions. \n- Sanitization: There is no evidence of input sanitization or filtering to mitigate potential injection attempts.
Audit Metadata