messaging-hierarchy
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided content which could theoretically contain instructions designed to influence the agent's behavior.
- Ingestion points: The skill accepts external text data including 'positioning statements', 'existing messaging documents', 'persona research', and 'proof points' (SKILL.md, Sections: Before You Start, Act 1, and Act 2).
- Boundary markers: The instructions do not define specific delimiters or guardrails to differentiate between the skill's instructions and user-supplied data, nor does it tell the agent to ignore instructions embedded in the inputs.
- Capability inventory: The skill contains no executable code, tool calls, network access, or file system operations. The risk is limited to the text generation context.
- Sanitization: There is no evidence of filtering or sanitization of input text before it is used in the messaging templates.
Audit Metadata