boring-copywriting
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user and reads from external configuration files, which presents a surface for indirect instructions.
- Ingestion points: The skill reads from multiple markdown files in the
world-code/directory and prompts the user for specific project context. - Boundary markers: There are no instructions to use XML tags or specific delimiters to isolate untrusted data from the prompt instructions.
- Capability inventory: The skill has no access to dangerous tools such as shell execution, file writing, or network operations, rendering the injection risk negligible.
- Sanitization: The skill does not perform explicit sanitization or filtering on the content of the foundation files before using them to generate copy.
Audit Metadata