skill-community-ops
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of user-supplied social media comments and event descriptions, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill ingests "评论内容" (comment content) and "负面事件描述" (negative event descriptions) defined in
SKILL.md. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potential commands embedded within the processed comments.
- Capability inventory: The skill does not request or use any capabilities for network operations, file system writes, or shell command execution. Its output is limited to text templates and analysis.
- Sanitization: No sanitization or filtering of the input content is mentioned in the logic.
Audit Metadata