wechat-viral-topic
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is a collection of Markdown instruction files (
SKILL.md,references/*.md,templates/*.md) providing a framework for content creation. It does not include any Python, JavaScript, or shell scripts. - [COMMAND_EXECUTION]: There are no instances of command execution, shell spawning, or privilege escalation patterns within the skill files.
- [DATA_EXFILTRATION]: No network-related commands (e.g.,
curl,wget,fetch) or hardcoded credentials (API keys, tokens, secrets) were detected. The skill does not access sensitive local file paths. - [PROMPT_INJECTION]: The skill's instructions are focused on guiding the agent through a content strategy workflow. No patterns designed to override system safety filters or disregard prior instructions were found.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied "raw materials" (news or project descriptions), it lacks any dangerous capabilities (network access, file writing, or code execution) that could be exploited by malicious input. Furthermore, the skill includes a risk checklist (
risk-checklist.md) specifically designed to filter out sensitive or non-compliant content.
Audit Metadata