oneshot-compute
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
@oneshot-agent/sdkNode.js package to provide orchestration and goal management capabilities. - [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection via the
objectiveparameter in theagent.computemethod. Ingestion point: theobjectivefield in SKILL.md; Boundary markers: none explicitly defined in the documentation; Capability inventory: the orchestrator performs research, lead enrichment, and email operations; Sanitization: not described in the documentation.
Audit Metadata