openspec-sdd

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @fission-ai/openspec package from the NPM registry to provide its core functionality. This is a vendor-owned package.
  • [COMMAND_EXECUTION]: The skill relies on the openspec CLI to perform actions such as initializing the project (openspec init), listing specifications, and archiving changes. These commands modify local files and directories.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its data processing workflow:
  • Ingestion points: Reads project context from openspec/config.yaml and analyzes existing codebase files in openspec/ directories.
  • Boundary markers: Absent; no explicit delimiters or instructions to ignore embedded commands are documented for these inputs.
  • Capability inventory: Executes CLI commands and performs file system operations including creation and modification of files.
  • Sanitization: Absent; the skill documentation does not specify validation or escaping of the ingested project data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:17 PM