042-planning-openspec

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends and automates the installation of the @fission-ai/openspec package from the npm registry, which is the official distribution channel for the OpenSpec toolset.
  • [COMMAND_EXECUTION]: Performs various CLI operations to manage the software development lifecycle, specifically using openspec --version, openspec init, openspec status, openspec show, openspec validate, and openspec archive.
  • [PROMPT_INJECTION]: The skill ingests data from implementation plan files (*.plan.md) to guide the creation of OpenSpec artifacts. This constitutes an indirect prompt injection surface where untrusted content in the plan files could attempt to manipulate the agent's logic. Ingestion points: Reads *.plan.md in Step 1. Boundary markers: None identified. Capability inventory: Command execution via openspec and npm. Sanitization: Relies on model-level safeguards.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:06 PM