un-ai-writing
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text drafts to identify and remove AI-writing signatures.\n
- Ingestion points: The agent ingests user-provided drafts as described in the workflow section of
SKILL.md.\n - Boundary markers: No specific delimiters or "ignore embedded instructions" headers are prescribed for the input text.\n
- Capability inventory: The skill definition does not include network operations, file system access, or shell command execution tools.\n
- Sanitization: The instructions do not specify any sanitization or validation of the input text before processing.\n- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions or reference files.
Audit Metadata