copy-editing

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it ingests and processes untrusted marketing copy provided by users.
  • Ingestion points: Marketing copy provided by the user in the prompt and the project-level context file .agents/product-marketing-context.md.
  • Boundary markers: Absent; the instructions do not mandate the use of delimiters like triple backticks or XML tags to isolate user-supplied content from the agent's core instructions.
  • Capability inventory: The skill's operations are limited to text analysis and generation; no external tools, network operations, or subprocess executions are defined in the provided files.
  • Sanitization: Absent; user-provided copy is processed directly without filtering or safety validation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:43 AM
Security Audit — agent-trust-hub — copy-editing