thread-writer-sms
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's logic is transparent and aligned with its stated purpose of generating multi-part social media content.\n- [COMMAND_EXECUTION]: The skill leverages the
create_posttool via the BlackTwist MCP. This functionality is restricted to publishing the generated thread content to the user's selected social media platforms.\n- [INDIRECT_PROMPT_INJECTION]: The skill acts on external source material provided by the user (articles, notes, drafts).\n - Ingestion points: User-provided text, articles, or notes in the input gathering phase in SKILL.md.\n
- Boundary markers: Absent.\n
- Capability inventory: Uses the
create_posttool to interact with social media platforms.\n - Sanitization: Absent.
Audit Metadata