copywriting
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest and process untrusted data from both the user prompt (drafts/briefs) and project-specific files like
.agents/product-marketing.md.\n - Ingestion points: The skill reads user-supplied copy and context from
.agents/product-marketing.mdor.claude/product-marketing.mdto inform its generation.\n - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the context files, which could allow malicious instructions to influence the agent's behavior.\n
- Capability inventory: The skill does not possess any tools or scripts for network communication, file system modifications, or shell command execution, which significantly mitigates the risk.\n
- Sanitization: The instructions do not specify any validation or filtering for the content ingested from the marketing context files.
Audit Metadata