version-bump-advisor
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data which could potentially contain malicious instructions aimed at influencing the versioning recommendation.
- Ingestion points: The skill accepts git diff output, PR descriptions, and natural language change lists as input in Step 1.
- Boundary markers: There are no specific instructions for the agent to use delimiters or ignore embedded commands within the processed data.
- Capability inventory: The skill is limited to generating text recommendations, changelog entries, and migration notes within the conversation. It does not execute shell commands, perform network operations, or write to the file system.
- Sanitization: The skill lacks explicit instructions to sanitize or validate the external content before analysis.
Audit Metadata