gplay-rollout-management

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous examples of shell command execution using the gplay CLI tool, jq for JSON parsing, and bc for calculations. These are intended for managing release tracks, updating rollout percentages, and monitoring application health.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to fetch and process external data from Google Play user reviews.
  • Ingestion points: Untrusted user review text enters the agent's context through the output of gplay reviews list (found in SKILL.md).
  • Boundary markers: No specific delimiters or warnings to ignore embedded instructions are provided in the examples.
  • Capability inventory: The skill utilizes shell execution for managing production releases, which could be targeted if the agent is influenced by malicious instructions within a review.
  • Sanitization: No sanitization or filtering of the review content is performed beyond simple JSON selection via jq.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:26 PM