gplay-vitals-monitoring
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill leverages the
gplayCLI to query app vitals and perform releases, and usesjqfor parsing results. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes stack traces and error issues from Google Play APIs, which are external data sources that could potentially harbor malicious content meant to influence agent behavior.
- Ingestion points: Output from
vitals errors reportsandvitals errors issuessubcommands in SKILL.md. - Boundary markers: No specific delimiters are used to separate API data from instructions.
- Capability inventory: Access to
gplayCLI for store management and shell execution for automation. - Sanitization: There is no evidence of sanitization or validation of the ingested error report data.
Audit Metadata