copywriting

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user prompts and local project files (e.g., .agents/product-marketing.md). While this creates a surface for indirect prompt injection where instructions could be embedded in the marketing context, the skill lacks high-risk capabilities like arbitrary command execution or network access, and standard LLM guardrails apply. This is a common and expected behavior for a specialized writing assistant.
  • [COMMAND_EXECUTION]: The skill does not contain any shell commands or dynamic execution patterns. It relies entirely on text processing and referencing internal markdown files.
  • [DATA_EXFILTRATION]: No network operations or external data transmissions are defined. The skill focuses on local file reading for context and text generation.
  • [PROMPT_INJECTION]: The instructions are well-defined and focused on the copywriting task. There are no patterns suggesting attempts to bypass safety filters or override system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:38 PM
Security Audit — agent-trust-hub — copywriting