aso
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for App Store Optimization (ASO) audits and uses standard tools to fetch public listing data. Analysis of the instructions, reference materials, and evaluation prompts reveals no evidence of malicious intent, credential theft, or unauthorized persistence mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it retrieves untrusted HTML content from external App Store and Google Play URLs.
- Ingestion points: External listing data is retrieved via the
WebFetchtool (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or specific safety instructions to isolate external content from the agent's core instructions.
- Capability inventory: The skill uses web-fetching, screenshot capture, and local file reading for marketing context (
.agents/marketing-strategy.md). - Sanitization: There is no explicit sanitization step for the fetched HTML content; however, the skill's focus on extracting specific metadata fields (like title, description, and character counts) inherently limits the execution potential of injected instructions.
Audit Metadata