aso-audit
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes untrusted data that could contain hidden instructions aimed at overriding the agent's behavior.
- Ingestion points: The skill reads a local file named
app-marketing-context.mdand fetches external data (app titles, descriptions, and reviews) via the Appeeky MCP or API. - Boundary markers: There are no delimiters or specific instructions provided to the agent to treat the ingested metadata as untrusted data or to ignore embedded instructions within that content.
- Capability inventory: The skill is limited to analysis and reporting; it does not contain scripts or commands for subprocess execution, file writing, or network operations to non-vendor domains.
- Sanitization: The skill lacks mechanisms to sanitize or validate the external metadata before it is incorporated into the agent's reasoning and output process.
Audit Metadata