gplay-reports-download
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Google Cloud Storage buckets into the agent's context, creating a surface for indirect prompt injection.
- Ingestion points: The
gplay reports downloadcommands (for both financial and statistics reports) retrieve external CSV and ZIP files which are then intended for agent processing. - Boundary markers: The provided instructions do not include specific delimiters or instructions to the agent to disregard potential commands embedded within the downloaded report data.
- Capability inventory: The skill performs shell command execution via the
gplayCLI and local file system writes to directories specified by the user. - Sanitization: There is no mention of sanitizing, validating, or filtering the contents of the downloaded reports before the agent processes them.
- [COMMAND_EXECUTION]: The skill uses shell-based commands for the
gplayCLI that interpolate user-provided parameters such as--bucket-id,--package, and--dir. If the agent or platform does not properly sanitize these inputs, it could lead to command injection vulnerabilities.
Audit Metadata