openspec-apply-change
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands using the
openspecCLI (e.g.,openspec list,openspec status, andopenspec instructions). These are standard operations for a development-focused skill and do not involve unauthorized privilege escalation or arbitrary system access. - [INDIRECT_PROMPT_INJECTION]: The skill reads task descriptions and context files from the
openspectool's output. While this presents an ingestion surface for potentially untrusted data, the skill includes guardrails to pause on ambiguous tasks or errors, reducing the risk of accidental obedience to embedded instructions. Severity is considered low. - [REMOTE_CODE_EXECUTION]: No remote code execution or external downloads were detected. All operations are performed locally using the pre-installed
openspecCLI.
Audit Metadata