social-x-post-card
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content to create design briefs used in file generation.
- Ingestion points: User messages are treated as instructions/briefs for the open-design workflow in SKILL.md.
- Boundary markers: None; there are no markers to differentiate the system instructions from the potentially untrusted user content.
- Capability inventory: The skill uses file-editing tools and MCP tools (prepare_open_design_brief, register_open_design_artifact) to output artifacts to the workspace as per SKILL.md.
- Sanitization: No sanitization or validation of the user brief is mentioned or implemented by the skill.
Audit Metadata