Skills
skills/luizhcrocha/skills/setup-luizrocha-skills/Gen Agent Trust Hub

setup-luizrocha-skills

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to run command-line tools to discover repository details. It utilizes git remote -v to identify the origin and relies on gh and glab CLIs to manage issues on GitHub and GitLab.
  • [EXTERNAL_DOWNLOADS]: The skill refers to the official GitLab CLI tool via its public repository on GitLab.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and utilizes content from multiple repository files.
  • Ingestion points: Analyzes files including AGENTS.md, CLAUDE.md, .git/config, CONTEXT.md, and CONTEXT-MAP.md.
  • Boundary markers: No specific delimiters are employed to separate the ingested file data from the skill's processing logic.
  • Capability inventory: The skill allows for the creation and modification of files such as CLAUDE.md, AGENTS.md, and the contents of the docs/agents/ directory.
  • Sanitization: There is no evidence of sanitization or validation performed on data retrieved from the repository before it is incorporated into the generated configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 03:35 PM
Security Audit — agent-trust-hub — setup-luizrocha-skills