optimize-post

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted manuscripts from user input or local files. This creates a surface for indirect prompt injection where instructions hidden within the input could attempt to influence the agent. However, the risk is minimal given the lack of dangerous capabilities.\n
  • Ingestion points: Manuscript text input or file path (WORKFLOW.md).\n
  • Boundary markers: None explicitly defined in the prompts to isolate user-provided text from system instructions.\n
  • Capability inventory: Text generation and clipboard access (WORKFLOW.md).\n
  • Sanitization: No specific input validation or sanitization routines are implemented.\n- [DATA_EXFILTRATION]: The skill includes functionality to read local files via user-provided paths for manuscript processing. This capability is inherent to its function but is restricted to the agent's file system permissions.\n- [COMMAND_EXECUTION]: The workflow involves copying generated text to the clipboard, which is a standard utility function for this type of content creation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 04:34 PM