write-in-my-voice
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The agent is instructed to ask users to paste "five recent posts they wrote themselves" or retrieve a voice profile from the
get_voice_profiletool (referencingSKILL.md). - Boundary markers: The instructions do not specify the use of delimiters (such as XML tags or triple backticks) or explicit warnings to the agent to ignore any instructions embedded within the user-provided posts.
- Capability inventory: The skill references tools for active operations, specifically
publish_postandschedule_post, which could be triggered by instructions embedded in the analyzed text if the agent lacks proper constraints. - Sanitization: There are no instructions for sanitizing or escaping the content retrieved from the user or the external API before it is processed by the LLM.
Audit Metadata