accelint-qrspi-propose

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests user-supplied ticket descriptions, feature requests, or problem statements which are then interpolated into sub-agent prompts during the planning phases.
  • Ingestion points: Phase 1 (Questions generation), Phase 3 (Design Scaffolding), and Phase 5 (Specs & Tasks generation) in SKILL.md.
  • Boundary markers: Present; the skill uses clear instructional headers (e.g., 'Research Findings:', 'Approved Design:') to delimit data blocks within the prompts.
  • Capability inventory: The skill executes shell commands via the openspec CLI and utilizes file modification tools (Edit) to manage architectural artifacts.
  • Sanitization: No explicit sanitization or filtering of the input strings is performed before interpolation into the prompt templates.
  • [COMMAND_EXECUTION]: The skill executes the openspec CLI tool to manage development workflows and configurations.
  • Commands include openspec config list, openspec config profile, and openspec update.
  • These commands are used to verify and configure the local environment for spec-driven development and are consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 04:11 PM