PDF Watermark
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within its intended scope of document modification. No evidence of obfuscation, exfiltration, or persistence was found.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted PDF files as input. 1. Ingestion points: User-provided PDF documents (SKILL.md). 2. Boundary markers: Absent; the prompt examples do not include delimiters to isolate content within the PDFs. 3. Capability inventory: 'add_watermark_to_pdf' (SKILL.md). 4. Sanitization: Absent. However, the potential impact is very low as the capability is restricted to document styling and lacks network or system access.
Audit Metadata