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.mddirect the agent to read.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdto 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