semantic-versioning
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project artifacts, including commit messages, public API definitions, and release notes, to determine versioning logic.
- Ingestion points: Manifests, package metadata, commit history, and project documentation are read into the agent context (SKILL.md).
- Boundary markers: The instructions lack explicit delimitation or sanitization requirements for external data parsed during version determination.
- Capability inventory: The skill instructions include writing to version manifests and package metadata files.
- Sanitization: No specific sanitization or escaping of data retrieved from the project environment is described.
Audit Metadata