mcp-media-inbox-triage
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from a shared Gmail inbox to perform classification and routing.
- Ingestion points: The skill reads the sender name, subject, and plain-text body of emails from Gmail as defined in
SKILL.mdandSETUP.md. - Boundary markers: The classification prompt in
SKILL.mdlacks explicit structural delimiters (like XML tags or triple quotes) to separate the untrusted email content from the agent's instructions. - Capability inventory: The skill possesses capabilities to write to Slack, Google Sheets, and create Gmail drafts via Zapier MCP as outlined in
SKILL.mdandSETUP.md. - Sanitization: While the skill instructs the AI to summarize rather than expose full email bodies, it does not include programmatic sanitization or escaping of the ingested text.
Audit Metadata