openspec-bulk-apply-change

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local CLI tools, specifically openspec and git, to automate the orchestration of project changes. These actions include listing changes, checking status, and creating isolated git worktrees.
  • [DATA_EXPOSURE]: The skill reads project context files and instructions generated by the openspec CLI. This data access is restricted to the local repository and is necessary for identifying the implementation scope of requested changes.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content derived from CLI outputs and source files.
  • Ingestion points: Instructions are ingested from the openspec instructions apply command and local contextFiles.
  • Boundary markers: No explicit markers are used to delimit external data from agent instructions.
  • Capability inventory: The skill can dispatch subagents and manipulate the local file system via git worktrees.
  • Sanitization: No filtering or sanitization of the ingested data is documented.
  • Mitigation: The risk of malicious instructions in ingested files is significantly reduced by the mandatory use of isolated worktrees and the strict prohibition of automatic merges or archiving without human review.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 11:01 AM
Security Audit — agent-trust-hub — openspec-bulk-apply-change