huashu-material-search
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local CSV and Markdown files which could theoretically contain instructions intended to influence the agent. Ingestion points: Reads from /Users/alchain/Documents/写作/写作参考/个人素材库/全部即刻动态.csv and other material files. Boundary markers: The instructions do not define specific delimiters to isolate external data from instructions. Capability inventory: The skill uses grep to read and search local file contents. Sanitization: No content filtering or validation is specified.
- [SAFE]: No malicious patterns, obfuscation, or high-risk behaviors were detected. All external references are to the author's own local filesystem.
Audit Metadata