reply-audit
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions involve retrieving lead data and campaign metrics from external services like Google Drive and Notion using platform-specific integrations.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing untrusted data from outreach replies.
- Ingestion points: Data is ingested from Google Sheets, Notion tables, CSV files, and outreach platform APIs (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill utilizes tool capabilities for reading files and creating new pages in Notion (SKILL.md).
- Sanitization: There are no explicit requirements to sanitize or escape the content of lead replies before they are processed by the agent.
Audit Metadata