asc-aso-audit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from App Store metadata fields (e.g., subtitle, keywords, and description) found in local JSON files under the
./metadatadirectory. These fields are analyzed for keyword usage and gaps. While this is the intended purpose of the skill, it creates a surface where malicious instructions embedded in the metadata could potentially influence the agent's behavior during the audit process.\n - Ingestion points:
metadata/app-info/{locale}.jsonandmetadata/version/{latest-version}/{locale}.json.\n - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions within the processed data.\n
- Capability inventory: The skill utilizes the
ascCLI for metadata management and theAstro MCPfor keyword research and tracking.\n - Sanitization: No explicit sanitization or filtering of the metadata content is mentioned before processing.\n- [COMMAND_EXECUTION]: The skill instructions describe the use of the
ascCLI tool to pull metadata, list app info, and apply keyword changes. These commands are integral to the skill's workflow for managing App Store metadata.\n- [EXTERNAL_DOWNLOADS]: The skill integrates withAstro MCPto fetch keyword rankings, competitor data, and suggestions from external sources. This external data is used to perform gap analysis as described in Phase 2.
Audit Metadata