designing-email-journeys
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information to generate campaign documentation, which presents a surface for indirect prompt injection.
- Ingestion points: The 'Discovery Questions' section in
SKILL.mdsolicits data from the user regarding their product, audience, and objectives. - Boundary markers: There are no instructions or delimiters provided to the agent to treat this user input as untrusted or to ignore any instructions embedded within it.
- Capability inventory: The skill instructs the agent to generate and deliver a comprehensive markdown (
.md) file containing the strategy and copy. - Sanitization: The skill does not implement or recommend any sanitization, filtering, or validation of the input data before it is interpolated into the output.
Audit Metadata