creating-user-stories

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to perform repository management tasks, including issue creation, label management, and project linking. These commands are integral to the skill's stated purpose of automating development workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted codebase data via the oracle tool to generate development plans, which creates a surface for indirect instructions to influence GitHub issue content.
  • Ingestion points: Codebase analysis performed by the oracle tool (SKILL.md).
  • Boundary markers: Uses a specific prompt template for the analysis tool to structure output, though it lacks explicit delimiters to separate data from instructions.
  • Capability inventory: Capabilities include reading the local filesystem (via oracle) and executing write operations to GitHub repositories (via gh CLI).
  • Sanitization: Relies on the agent's logic and the provided template; no specific sanitization of input codebase data is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 01:05 PM
Security Audit — agent-trust-hub — creating-user-stories