copy-editing
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted marketing copy provided by the user.
- Ingestion points: The skill accepts user-provided text for editing through prompts like 'edit this copy' or 'review my copy', as described in
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters (e.g., XML tags or clear 'ignore embedded instructions' warnings) to prevent the model from obeying instructions hidden within the copy being edited.
- Capability inventory: While the skill primarily performs text transformation, it has the capability to read local context files like
.agents/product-marketing.md, which could be exploited if an injection directs the agent to disclose context content. - Sanitization: No sanitization or validation of the input text is performed before it is processed by the editing framework.
Audit Metadata