screenshot-text
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use a specific CLI tool (
aso) to perform keyword research. This involves executing shell commands with parameters like<top_keywords>and<SF>(storefront). While these are standard for App Store Optimization tasks, they represent a capability to run subprocesses. - [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection because it ingests untrusted external data (App ID, feature lists, and audience descriptions) which are then used to influence the agent's logic and the parameters of the research command.
- Ingestion points: User-provided App ID, feature lists, and competitor context in
SKILL.md. - Boundary markers: Absent. The skill does not provide delimiters or instructions to ignore potential commands embedded in the processed app data.
- Capability inventory: Shell command execution via the
asoCLI tool. - Sanitization: Absent. There are no instructions for the agent to sanitize or validate the user-provided data before using it in the workflow or CLI commands.
Audit Metadata