app-marketplace-listing-standards
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed entirely of Markdown instructions (
SKILL.md), reference documents (references/), and evaluation cases (evals/). No scripts (Python, JavaScript, shell) or binaries are included. - [SAFE]: No malicious patterns were detected across the analyzed threat categories. The skill's instructions focus on generating a rulebook for marketplace listing standards based on user-provided interview answers and internal benchmark data.
- [DATA_EXPOSURE]: There are no hardcoded credentials, sensitive file paths, or network exfiltration patterns. The reference to
developer-platform-context.mdis a standard mechanism for optional memory persistence within this vendor's ecosystem. - [REMOTE_CODE_EXECUTION]: There are no patterns involving remote script execution, package installation, or dynamic evaluation of external content.
- [PROMPT_INJECTION]: The skill instructions do not contain DAN-style jailbreaks, instructions to ignore safety guidelines, or attempts to extract system prompts. The "Memory (advised)" section is a standard structural component for long-running agent tasks.
- [OBFUSCATION]: Manual and automated scanning found no evidence of Base64 encoding, zero-width characters, homoglyphs, or other techniques used to hide malicious intent.
Audit Metadata