deploy

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill executes build and deployment tasks using npm run build and pa app push. These are standard operations for a CI/CD-focused skill. The use of npx --no-install for the pa command is a safety-oriented pattern that ensures the tool is executed from the local project environment without downloading unauthorized packages.
  • Indirect Prompt Injection Surface: The skill reads project context from a memory-bank.md file (Step 1). While this is a standard workflow for maintaining project state, it represents a potential surface for indirect prompt injection if the file contains instructions intended to influence agent behavior.
  • Ingestion points: The agent reads memory-bank.md during the 'Check Memory Bank' step.
  • Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are present in the skill's logic.
  • Capability inventory: The skill possesses Bash execution capabilities (for building and pushing apps) and Write capabilities (for updating the memory bank).
  • Sanitization: There is no explicit sanitization of the content read from the metadata file before it is used to inform the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:15 AM
Security Audit — agent-trust-hub — deploy