trigger-dev
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for background tasks that process untrusted data from external sources.
- Ingestion points: Task definitions in
SKILL.mdand reference files ingest external data viapayloadarguments (e.g.,payload: { data: string }). - Boundary markers: The instructions do not specify the use of delimiters or boundary markers to differentiate between data and instructions within these payloads.
- Capability inventory: The skill includes tools with significant execution capabilities, such as
mcp__trigger__deployandmcp__trigger__trigger_task. - Sanitization: The provided code snippets and rules do not include instructions for sanitizing or escaping content within task payloads before processing.
Audit Metadata