partnership-outreach-writer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data during its partnership definition workflow. \n
- Ingestion points: User-provided input for partner type, offer, and objective in SKILL.md.\n
- Boundary markers: Absent; instructions do not use delimiters to wrap user content.\n
- Capability inventory: The skill utilizes Read and Write tools to manage generated outreach content.\n
- Sanitization: Absent; no filtering or validation is performed on the user-supplied values before they are used in the workflow sequence.\n- [SAFE]: The skill references the vendor's official domain
https://infloq.comin both SKILL.md and plugin.json. These references are used appropriately to provide examples and metadata about the skill's origin and do not involve data exfiltration or unauthorized network activity.
Audit Metadata