copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and reference data. No executable scripts, network requests, or credential exposures were found.
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to read context from
.agents/product-marketing-context.mdto inform its copywriting. - Ingestion points: The
SKILL.mdfile instructs the agent to read.agents/product-marketing-context.mdor.claude/product-marketing-context.mdat the start of the task. - Boundary markers: The skill does not define specific delimiters for this content.
- Capability inventory: The skill does not use any tools or commands that allow for file writing, network communication, or code execution.
- Sanitization: No sanitization is applied to the ingested context.
Audit Metadata