asc-aso-rankings
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs file system operations (read and write) at a hardcoded absolute directory path: /Users/antonnovoselov/Documents/Vault/Projects/VivaDicta/ASO/. It also executes the external tool mcp__astro__get_app_keywords to retrieve keyword rankings for specific application IDs.
- [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection as it ingests and processes untrusted data from both external API responses and local markdown files.
- Ingestion points: Data is read from app-store-keywords.md, previous rankings files (rankings/*.md), and the results of the Astro MCP tool call.
- Boundary markers: The skill does not provide the agent with specific delimiters or instructions to treat the ingested data as non-executable or to ignore instructions potentially embedded within those files.
- Capability inventory: The skill possesses the capability to write new files to the filesystem and invoke external MCP tools based on parsed data.
- Sanitization: There is no evidence of content validation or sanitization for the data retrieved from the local vault or the external API before it is processed or used to generate new output files.
Audit Metadata