command-aso-pass
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data by pulling current app listing states and Apple Search Ads (ASA) conversion data during the research phase. While this ingestion of external content creates a surface for indirect prompt injection, the risk is mitigated by explicit instructions requiring the agent to obtain user authorization before performing impactful actions such as metadata publication or sending review replies.
- Ingestion points: SKILL.md (Workflow steps 2 and 3 pull external state and ASA data).
- Boundary markers: Not explicitly defined in instructions.
- Capability inventory: Metadata publication and reply drafting (SKILL.md, steps 7 and 8).
- Sanitization: Not explicitly defined.
Audit Metadata