pct-application
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and requested tools (Bash, Read, Write) are appropriately restricted to the domain of patent application formalities and document processing.
- [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized network operations was found.
- [PROMPT_INJECTION]: The skill processes untrusted intellectual property drafts. Ingestion points: Patent application documents and invention disclosures (SKILL.md). Boundary markers: Absent. Capability inventory: Bash, Read, and Write tools. Sanitization: Absent. This ingestion is essential for the skill's primary function and does not represent a malicious finding.
Audit Metadata