setup-ai-native-development

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to list and install external packages from mattpocock/skills using the npx command.
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and the npx package runner to perform environment discovery and skill management tasks.
  • [DATA_EXFILTRATION]: The skill reads repository metadata, git remote configurations, and GitHub authentication status to determine setup requirements and backend compatibility.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ingestion of untrusted data from repository files. 1. Ingestion points: .and/config.yml, root AGENTS.md / CLAUDE.md, and GitHub issue descriptions. 2. Boundary markers: No delimiters or explicit instructions to ignore embedded commands are specified for the ingested content. 3. Capability inventory: The agent has the capacity to write to the local file system and modify GitHub repository labels. 4. Sanitization: The skill does not describe any sanitization or validation logic for data read from the repository files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 07:07 AM
Security Audit — agent-trust-hub — setup-ai-native-development