copy-editing
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied marketing copy and local context files, which can potentially contain malicious instructions intended to subvert the agent's behavior.
- Ingestion points: The skill ingests user text for editing and reads the
.agents/product-marketing-context.mdfile (referenced inSKILL.md) for brand alignment. - Boundary markers: The instructions do not define specific delimiters or guardrails to isolate user data from the agent's instruction set.
- Capability inventory: The skill is restricted to text processing as described in
SKILL.mdand does not request high-risk permissions such as network communication, file system modifications, or command execution. - Sanitization: The instructions do not include steps to sanitize or validate the user-provided content before the editing process begins.
Audit Metadata