Skills
Navigate
skills/yasserstudio/gpc-skills/gpc-metadata-sync/Gen Agent Trust Hub

gpc-metadata-sync

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The detection script scripts/detect_gpc.mjs executes shell commands using execSync to verify the installation and configuration of the GPC CLI.
  • Evidence: execSync("gpc --version"), execSync("npx gpc --version 2>/dev/null"), and execSync("gpc auth status --json 2>/dev/null") in scripts/detect_gpc.mjs.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to pull and push metadata (titles, descriptions, changelogs) from the Google Play Console, which involves ingesting external, untrusted text that could contain malicious instructions.
  • Ingestion points: gpc listings pull and gpc listings get (mentioned in SKILL.md).
  • Boundary markers: The instructions do not specify prompt-level delimiters or 'ignore' warnings for the synced metadata content.
  • Capability inventory: The skill uses the gpc CLI, which has the capability to perform network operations, file writes, and image uploads to the Google Play Store.
  • Sanitization: The skill documentation in SKILL.md (Security notes section) highlights that the CLI tool implements lstat() checks to prevent symlink traversal and CSV cell prefixing to prevent formula injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 08:48 AM