post-formatter
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a pure text-generation utility that takes user input to create LinkedIn posts. It does not utilize any tools (as confirmed by the lack of frontmatter permissions) or perform network/file system operations.- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting untrusted user content (topics or context dumps) in Step 1. However, since the skill has no capabilities (no tools, shell commands, or network access), any malicious instructions embedded in the input data cannot be executed, rendering the surface benign. Evidence Chain: 1. Ingestion Points: Step 1 (AskUserQuestion). 2. Boundary Markers: None. 3. Capability Inventory: None. 4. Sanitization: None.
Audit Metadata