openspec-verify-change
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
openspecCLI tool using several subcommands (list,status,instructions apply) to retrieve metadata and file lists from the local development environment for verification. - [PROMPT_INJECTION]: Indirect prompt injection surface identified as the skill ingests potentially untrusted data from the repository. Ingestion points: The skill reads implementation tasks (
tasks.md), design decisions (design.md), and requirement specifications from theopenspec/changes/directory. Boundary markers: The skill logic does not utilize specific delimiters or instructions to ignore embedded commands or instructions within these ingested files. Capability inventory: The skill possesses the ability to execute CLI commands and perform broad searches across the local codebase based on extracted keywords. Sanitization: There is no evidence of sanitization or validation of the requirement names or scenario descriptions before they are used in search operations or report generation.
Audit Metadata