breaking-changes-management
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided technical descriptions of code changes to generate documentation, presenting a standard attack surface for indirect prompt injection.
- Ingestion points: Technical descriptions of breaking changes provided by the user or identified from the codebase (SKILL.md Workflow steps 1-4).
- Boundary markers: Absent; the instructions do not explicitly prompt the agent to use delimiters for external data.
- Capability inventory: The skill uses
scripts/migration-guide-scaffold.pyto write markdown templates to the local filesystem. - Sanitization: Absent; content is interpolated directly into markdown templates.
- [COMMAND_EXECUTION]: The skill includes a local Python utility
scripts/migration-guide-scaffold.pyused to generate documentation skeletons. This script performs basic file writing based on user-supplied arguments and does not involve network access or sensitive data processing. - [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or malicious persistence was found across the analysis of all files.
Audit Metadata