NYC

blog-post-writer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION] (SAFE): The skill contains instructional patterns to guide writing style but does not attempt to bypass safety filters or override system instructions.
  • [DATA_EXFILTRATION] (SAFE): No network requests or sensitive file access patterns were detected. The skill only references local documentation files for writing style guidance.
  • [COMMAND_EXECUTION] (SAFE): The skill does not execute any shell commands or use any dynamic code execution functions like eval() or exec().
  • [EXTERNAL_DOWNLOADS] (SAFE): No external dependencies are installed, and no remote scripts are downloaded.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process untrusted user input ('brain dumps') as a primary function.
  • Ingestion points: The process starts by accepting unstructured text provided by the user in Step 1.
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded commands within the brain dump.
  • Capability inventory: The skill is restricted to text generation and lacks capabilities like file writing, network access, or command execution.
  • Sanitization: None; the input is processed directly into the creative writing workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM