Skills
skills/mvanhorn/printing-press-library/pp-cloud-run-admin/Gen Agent Trust Hub

pp-cloud-run-admin

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions and metadata to install CLI and MCP binaries from the vendor's own repositories using npx and go install (e.g., github.com/mvanhorn/printing-press-library).- [DATA_EXFILTRATION]: The cloud-run-admin-pp-cli tool includes a --deliver webhook:<url> flag that allows command results to be transmitted to external URLs via HTTP POST. It also includes a feedback mechanism that can be configured to send data to a remote endpoint.- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using a custom binary to interact with the Cloud Run Admin API.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests and processes resource metadata from Google Cloud Run which could contain malicious instructions. Ingestion points: services list, sync, and search commands in SKILL.md. Boundary markers: Absent. Capability inventory: Administrative shell command execution and network data delivery via the cloud-run-admin-pp-cli binary. Sanitization: None mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 08:32 PM
Security Audit — agent-trust-hub — pp-cloud-run-admin