skills/mtent/speshul-skills/aso/Gen Agent Trust Hub

aso

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill retrieves metadata and listing information from official platforms such as the Apple App Store and Google Play Store. These are well-known, legitimate services, and the data is used for its intended auditing purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external app descriptions which are technically attacker-controlled. However, the risk is minimized as the skill focuses on text generation and does not invoke dangerous system tools, execution environments, or network exfiltration commands.
  • Ingestion points: External App Store and Google Play URLs processed during the audit phase (references/store-audit.md).
  • Boundary markers: None provided in the instructions to separate external listing content from internal logic.
  • Capability inventory: Limited to text analysis, scoring, and report generation; no shell execution, file-system writing, or remote code execution capabilities identified.
  • Sanitization: Content is processed as-is without explicit filtering or sanitization steps mentioned in the prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:55 AM
Security Audit — agent-trust-hub — aso