app-store-keyword-ops
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources that may contain malicious instructions designed to influence the agent's output or keyword recommendations.
- Ingestion points: The skill reads competitor keywords, app listings, and reviews through tools like
Astro MCP,app-store-scraper, andaso(SKILL.md). - Boundary markers: Section 3 defines 'Gate' checks (Product fit, Locale fit) and Section 5 mandates an explicit human-in-the-loop confirmation before any write operation is executed.
- Capability inventory: The skill has the capability to write metadata to App Store Connect using the
helm-asctool (SKILL.md). - Sanitization: Section 2 specifies normalization of tokens using Unicode NFC, comma splitting, and whitespace removal.
- [COMMAND_EXECUTION]: The skill relies on the execution of several external CLI tools and MCP servers to perform its core functions.
- Evidence: SKILL.md instructs the agent to use
Astro MCP,app-store-scraper,aso, andhelm-ascfor resolving app identifiers, capturing baselines, and applying keyword updates.
Audit Metadata