developmental-edit
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied writing drafts, creating a potential surface where malicious instructions embedded in the draft could influence the agent's behavior.
- Ingestion points: The skill explicitly requests the user's full draft for analysis.
- Boundary markers: The instructions do not specify using delimiters to isolate the user-provided draft from the system instructions.
- Capability inventory: The skill can trigger tool calls to save analyzed content to a connected notes application or the vendor's "Scratchpad connector."
- Sanitization: There are no instructions to sanitize or validate the content of the draft before it is processed or saved to external tools.
Audit Metadata