landingpage-readme

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing a supplementary 'copywriting' skill from the author's own repository using npx skills add eliasstravik/skills. This is a vendor-provided resource and follows standard extension practices.
  • [COMMAND_EXECUTION]: The skill generates and executes gh (GitHub CLI) commands to update repository metadata (About description, topics, social preview). Security risk is mitigated by a mandatory requirement for explicit user approval before any command execution.
  • [SAFE]: The skill processes untrusted data from the local repository (code, README, docs) to derive documentation content. While this presents an indirect prompt injection surface, the skill implements a strong security posture by requiring the agent to present all proposed changes and commands to the user for approval before performing any mutations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:16 PM
Security Audit — agent-trust-hub — landingpage-readme