content-creator
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [Prompt Injection] (MEDIUM): Deceptive Metadata and Identity Spoofing. The skill's YAML metadata includes 'verified: true' and identifies the author as 'Claude Skills Team'. These are self-authoritative claims that can mislead users about the skill's official verification and origin, which is classified as Metadata Poisoning.
- [Prompt Injection] (LOW): Indirect Prompt Injection Surface. The skill is designed to ingest and process untrusted external data from files like 'content.txt' and 'article.md'. There are no documented boundary markers or instructions to ignore embedded commands, and the skill lacks mentioned sanitization procedures for this data.
- [Command Execution] (SAFE): The skill provides examples for executing local Python scripts. No malicious command injection patterns were identified in the documentation provided.
Audit Metadata