Skills
skills/officialunofficial/skills/setup-skills/Gen Agent Trust Hub

setup-skills

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes git remote -v and inspects .git/config to identify the repository's origin (e.g., GitHub or GitLab) and suggest the appropriate issue tracker integration.
  • [PROMPT_INJECTION]: The skill ingests content from AGENTS.md and CLAUDE.md to determine if previous setup has occurred. This creates a surface for indirect prompt injection where malicious instructions embedded in those files could influence the agent during the configuration process.
  • Ingestion points: Reads AGENTS.md and CLAUDE.md from the repository root during the initial exploration phase.
  • Boundary markers: Absent. The instructions do not specify using delimiters or warnings to ignore instructions within the project files being read.
  • Capability inventory: The skill can perform file system writes to docs/agents/, edit CLAUDE.md/AGENTS.md, and execute git commands.
  • Sanitization: Absent. There is no explicit validation or escaping of the content retrieved from project files before it is processed or summarized.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 06:17 PM
Security Audit — agent-trust-hub — setup-skills