email-copywriter
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill instructions confirms that the content is strictly limited to providing copywriting guidelines and structural templates for email creation. There are no instances of command execution, file system access, or network requests within the skill definition.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its core function of ingesting and processing user-provided content into its output.
- Ingestion points: The 'Required Input' section in SKILL.md identifies multiple user-supplied fields such as 'Key message' and 'Offer or content to feature'.
- Boundary markers: The instructions do not define specific delimiters or security warnings to isolate user input from the skill's instructions.
- Capability inventory: No dangerous capabilities such as network access, file writing, or subprocess execution are identified in the skill content.
- Sanitization: There are no provided mechanisms for sanitizing or filtering the user-provided inputs.
Audit Metadata