gplay-rollout-management
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides commands to fetch and process user reviews from Google Play, which introduces a surface for indirect prompt injection from untrusted user content.
- Ingestion points:
gplay reviews listcommand inSKILL.mdused to monitor user feedback. - Boundary markers: Absent; there are no instructions or delimiters to isolate user-generated text from agent instructions.
- Capability inventory: Command execution via
gplay,jq,bc, and./gradlewbuild scripts. - Sanitization: Absent; the fetched review text is processed directly without validation or filtering.
- [COMMAND_EXECUTION]: The skill utilizes local CLI tools (
gplay,jq,bc,gradlew) to perform its primary functions of release management and status monitoring. This is consistent with the skill's stated purpose.
Audit Metadata