openspec-apply-change

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing local shell commands via the openspec CLI tool to manage change tasks, specifically using commands like openspec list, openspec status, and openspec instructions apply.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests external file content and dynamic instructions while possessing the ability to modify files and execute CLI commands.
  • Ingestion points: The skill reads multiple files specified by the CLI output (under contextFiles), including proposals, design documents, and task lists, as well as a 'dynamic instruction' field.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded commands when reading these context files or the dynamic instructions.
  • Capability inventory: The skill can execute shell commands via the openspec CLI and perform file write operations to update task checklists.
  • Sanitization: The skill lacks explicit sanitization steps for the content ingested from the project files or the dynamically generated instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 08:20 PM
Security Audit — agent-trust-hub — openspec-apply-change