openspec-apply-change
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
openspecCLI commands such asopenspec list,openspec status, andopenspec instructionsto retrieve change metadata and implementation instructions in JSON format. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external files to drive agent actions, creating a surface for indirect prompt injection.
- Ingestion points: Content from files identified in the
contextFilesoutput of theopenspecCLI, such as proposals, specifications, and task lists. - Boundary markers: Absent; the skill lacks specific delimiters or instructions to ignore embedded commands in the processed files.
- Capability inventory: File system read/write access and local command execution through the
openspecCLI. - Sanitization: Absent; the skill does not sanitize or validate task descriptions or file content before the agent implements the requested changes.
Audit Metadata