copywriting-core
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing and rewriting copy provided by users, which serves as a data ingestion point for potential indirect prompt injection. If the input text contains malicious instructions, the agent could be influenced to deviate from its intended behavior or incorrectly modify project files.
- Ingestion points: The skill ingests user-provided text for editing and reads strategy-related files such as
strategy/brand.mdandabout/me.mdfrom the local workspace. - Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores or isolates instructions that may be embedded within the copy provided for editing.
- Capability inventory: The skill is authorized to read and write markdown files within the
strategy/,about/, andcontent/directories. - Sanitization: The skill does not implement any validation, escaping, or sanitization of the input text before processing it.
Audit Metadata