carousel-writer-sms
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not contain any malicious instructions, obfuscated code, or unauthorized network calls.- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by reading context from a local file. However, this is used solely for content generation and is considered safe within the skill's intended use case.
- Ingestion points: .agents/social-media-context-sms.md (referenced in SKILL.md)
- Boundary markers: Absent.
- Capability inventory: Text output generation. No system commands, network requests, or file write operations were detected.
- Sanitization: Absent.- [COMMAND_EXECUTION]: The skill includes clear boundaries and does not execute arbitrary shell commands or access external APIs. References to BlackTwist MCP are related to the vendor's own infrastructure and do not indicate a security risk.
Audit Metadata