gplay-release-flow

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest external data, including release notes and build artifacts, which could contain malicious content. This represents an indirect prompt injection surface when paired with the agent's ability to execute production-level deployment commands.
  • Ingestion points: Release notes files and application artifacts (.aab, .apk) mentioned in SKILL.md and obb.md.
  • Boundary markers: The instructions do not provide explicit delimiters or warnings to the agent to treat external file content as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill enables the agent to use the gplay CLI for network communication with Google Play services and to modify release tracks.
  • Sanitization: There are no instructions for validating or sanitizing the content of external files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:59 PM
Security Audit — agent-trust-hub — gplay-release-flow