changeset-pr
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local git operations and the Changesets CLI tool via Python scripts. These use
subprocess.runwith argument lists, effectively mitigating shell injection risks.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local package files and changeset markdown which could be contributor-controlled. - Ingestion points: Reads
.changeset/*.mdandpackage.jsonfiles viascripts/inspect_changeset_scope.py. - Boundary markers: Absent.
- Capability inventory: Includes file system writes and local command execution.
- Sanitization: Content is parsed for structure but not sanitized for prompt-based instructions.- [SAFE]: No network access, remote code downloads, or obfuscation techniques were identified.
Audit Metadata