copy-editing
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided text for copy-editing. This creates a surface for indirect prompt injection, although the risk is minimal given the skill's focus on text processing.
- Ingestion points: User-supplied marketing copy provided for editing or review as defined in SKILL.md.
- Boundary markers: The skill instructions do not specify any delimiters or safety warnings for the agent to ignore instructions embedded within the user's copy.
- Capability inventory: The skill is instructed to read a project-specific marketing context file located at
.claude/product-marketing-context.md(SKILL.md). - Sanitization: There are no explicit instructions to sanitize or filter the input text before the agent processes it for editing.
Audit Metadata