caption-writer-sms

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill reads from a local context file located at .agents/social-media-context-sms.md to understand the user's brand voice and audience. This is an expected behavior for personalization within the agent's workspace and does not target sensitive system files or credentials.
  • [COMMAND_EXECUTION]: The skill mentions the use of a create_post tool via the BlackTwist MCP to automate the scheduling and publishing of social media content. This functionality is directly aligned with the skill's stated purpose and utilizes the author's own toolset.
  • [PROMPT_INJECTION]: The skill incorporates an indirect prompt injection surface by ingesting user-provided visual descriptions and goals to generate content. This is a standard risk for any generative AI task and is handled through clear instructional boundaries for the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 11:15 AM