copy-editing
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no executable code, script references, or external dependencies. Its functionality is limited to providing linguistic and structural feedback on text. No malicious patterns, command executions, or network activities were found.
- [INDIRECT_PROMPT_INJECTION]: The skill acts on untrusted user-provided text for editing.
- Ingestion points: User-provided copy as defined in the skill triggers (e.g., 'edit this copy').
- Boundary markers: The instructions do not define specific delimiters to isolate the copy from the agent's instructions.
- Capability inventory: None; the skill does not request or use any tools, shell access, or network permissions.
- Sanitization: No sanitization or filtering of input text is performed.
- Risk Assessment: Because the skill lacks external capabilities or tool access, the potential for harm via indirect injection is negligible.
Audit Metadata