copywriting-prose-creator
Warn
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill provides Python scripts in references/audit-tools.md for analyzing sentence length distribution and n-gram frequencies. The instructions in SKILL.md direct the agent to execute these scripts on the provided content corpus.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests a content corpus from files or external URLs without boundary markers or sanitization, creating a surface where malicious instructions in the corpus could influence agent behavior. Ingestion points include local folders and external URLs. The agent's capability inventory includes file writing, web fetching, and script execution.
- [COMMAND_EXECUTION]: The skill uses tools like Grep and shell commands like wc and grep -iE to perform quantitative audits on content corpora.
Audit Metadata