open-source-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly instructional, providing templates for GitHub optimization and community management. It references well-known tools like Octolens and Shields.io. No suspicious commands or network activities were found.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local file to understand the developer audience.\n
- Ingestion points: Reads
.agents/developer-audience-context.mdas specified inSKILL.md.\n - Boundary markers: The instructions do not define delimiters for the ingested context data.\n
- Capability inventory: The skill has no execution or network capabilities; it only provides text-based guidance.\n
- Sanitization: No filtering or sanitization of the context file content is instructed.
Audit Metadata