community-building
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: No malicious behaviors or security risks were identified. The skill contains instructional content and message templates designed for community management.
- [EXTERNAL_DOWNLOADS]: The skill references established tools and services such as Octolens, MEE6, Carl-bot, and Luma. These are recognized services in the community management ecosystem and are not used for remote code execution.
- [PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection by reading from the local file
.agents/developer-audience-context.md. Ingestion point:.agents/developer-audience-context.md(SKILL.md). Boundary markers: Absent. Capability inventory: None; the skill generates text templates and recommendations but does not utilize shell tools, file-writing tools, or network-writing capabilities. Sanitization: Absent. The risk is evaluated as safe because the skill lacks the necessary capabilities to act on or exfiltrate potentially malicious content within the ingested file.
Audit Metadata