play-developer-console

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data that could contain malicious instructions.
  • Ingestion points: The skill reads external app reviews via play reviews list and processes local files in play/release-notes/ and play/metadata/.
  • Boundary markers: There are no explicit instructions or markers to distinguish between data and commands when processing these inputs.
  • Capability inventory: The agent has the ability to execute shell commands (play, bun), modify local project files, and patch the CLI tool source code.
  • Sanitization: No evidence of sanitization, validation, or escaping of the ingested external content is present.
  • [COMMAND_EXECUTION]: The skill instructions rely heavily on the execution of shell commands through a locally linked CLI (play) and the Bun runtime.
  • Evidence: Instructions include running play metadata validate, play tracks release, bun run typecheck, and bun test within specific local directory paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:11 AM
Security Audit — agent-trust-hub — play-developer-console