skills/frumu-ai/tandem/copywriting/Gen Agent Trust Hub

copywriting

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill follows a benign workflow for drafting marketing documentation using provided templates.
  • [NO_CODE]: The skill consists of markdown instructions and templates with no executable scripts or binary components.
  • [PROMPT_INJECTION]: The skill ingests data from external web sources and internal files to generate marketing drafts. This is an ingestion surface for indirect prompt injection. 1. Ingestion points: product-marketing-context.md and web browsing results. 2. Boundary markers: No explicit delimiters are used for external data. 3. Capability inventory: The agent is limited to creating markdown files. 4. Sanitization: No explicit validation of external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:08 PM
Security Audit — agent-trust-hub — copywriting