skills/glebis/claude-skills/repo-prep/Gen Agent Trust Hub

repo-prep

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches license templates from the SPDX official GitHub repository and .gitignore templates from the GitHub gitignore repository. These are recognized as well-known and trusted external sources.
  • [PROMPT_INJECTION]: The 'Authorship Wizard' feature introduces a surface for indirect prompt injection.
  • Ingestion points: The skill is instructed to gather evidence from the repository being processed, including reading git log output, CHANGELOG.md, README.md, Architectural Decision Records (ADRs) in the docs/ directory, and AI context files like CLAUDE.md or AGENTS.md.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate ingested data from agent instructions during this process.
  • Capability inventory: The skill can write files to the local system, execute bundled Python scripts, and invoke the GitHub CLI (gh) for repository management tasks.
  • Sanitization: The instructions do not define any validation or sanitization steps for the data retrieved from external files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 09:05 PM
Security Audit — agent-trust-hub — repo-prep