copywriting

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates a vulnerability surface for indirect prompt injection by design through its context-gathering mechanism.\n
  • Ingestion points: The skill instructions in SKILL.md direct the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md to gather context before responding.\n
  • Boundary markers: There are no instructions to use boundary markers or explicit directives for the agent to ignore instructions that might be embedded in these context files.\n
  • Capability inventory: The skill is primarily focused on text generation for marketing copy and does not explicitly list dangerous tool permissions in its frontmatter, though it utilizes file-reading capabilities to ingest context.\n
  • Sanitization: Content retrieved from project files is not subjected to sanitization or validation before being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:07 PM
Security Audit — agent-trust-hub — copywriting