copy-editing

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided marketing copy and external files for review and editing.
  • Ingestion points: The skill instructions in SKILL.md direct the agent to review and edit "existing marketing copy" and read .agents/marketing-context.md.
  • Boundary markers: There are no explicit instructions or delimiters defined to distinguish between user-provided data and the agent's control instructions.
  • Capability inventory: The skill utilizes text processing and analysis tools; no high-risk capabilities like network exfiltration or shell execution are explicitly invoked in the scripts.
  • Sanitization: The instructions do not include requirements for sanitizing or filtering input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:55 AM
Security Audit — agent-trust-hub — copy-editing