copy-anatomy
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied copywriting text to extract frameworks and create templates. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the copy being analyzed.
- Ingestion points: The skill accepts arbitrary text via the primary input argument.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the input text.
- Capability inventory: The skill has no access to sensitive tools, network operations, or file system modifications; it only generates Markdown text output.
- Sanitization: The core function of the skill—replacing specific details with generic variables—serves as a natural structural filter for the final output.
Audit Metadata