competitor-aso-teardown
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a shell command block intended to be executed by the agent to install tools and perform data scraping via a Node.js script.- [EXTERNAL_DOWNLOADS]: The skill references and installs the 'app-store-scraper' package from the npm registry, a well-known service for developer dependencies.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted external content (app store descriptions and user reviews) into the agent's context. 1. Ingestion points: Output of the app-store-scraper command in SKILL.md. 2. Boundary markers: Absent in the scraping script. 3. Capability inventory: No dangerous capabilities are executed on the ingested data within the provided scripts. 4. Sanitization: Absent.
Audit Metadata