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 openspec CLI 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 the openspec/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
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 PM