ai-writing-auditor
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted 'target content' without using security boundaries or delimiters. This allows instructions embedded in the analyzed text to potentially influence agent behavior.
- Ingestion points: Processes external prose provided for auditing and rewriting in SKILL.md.
- Boundary markers: Absent. No delimiters or 'ignore' instructions are used to isolate user data from the agent instructions.
- Capability inventory: The skill is configured with 'workspace-write' permissions, allowing file modification within the workspace.
- Sanitization: No content validation or sanitization is performed on the processed text before it is handled by the agent.
Audit Metadata