App Store Copy
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied app details, features, and competitor information to generate store listings. While it lacks explicit boundary markers or sanitization instructions for this input, it possesses no dangerous capabilities such as network access, file system writes, or command execution that could be leveraged if malicious instructions were embedded in the input data.
- Ingestion points: Process section in SKILL.md ("Gather: app name, what it does, top 3 features...").
- Boundary markers: Absent.
- Capability inventory: None detected. The skill only performs text generation within the LLM context.
- Sanitization: Absent.
- [SAFE]: No malicious patterns, obfuscation, credential harvesting, or unauthorized remote code execution patterns were detected in the skill instructions.
Audit Metadata