voice-memo-cleanup
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data in the form of voice memo transcripts, which presents a surface for indirect prompt injection attacks where malicious instructions could be embedded in the text.\n
- Ingestion points: The skill reads voice memo transcripts, dictations, or speech-to-text drafts provided by the user (SKILL.md).\n
- Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate the input text from the agent's instructions, nor do they include warnings to ignore embedded commands.\n
- Capability inventory: The skill can perform write operations by interacting with connected note-taking apps or the 'Scratchpad connector' to save or update notes (SKILL.md).\n
- Sanitization: There are no instructions provided to sanitize, validate, or escape the content of the transcript before it is processed or saved to external tools.
Audit Metadata