pdf-watermark-remover

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external PDF files and explicitly instructs the agent to 'inspect' their content. This creates a surface for indirect prompt injection where malicious text embedded within a PDF could attempt to override agent instructions or behavior during the inspection or verification steps.
  • Ingestion points: The agent is instructed in SKILL.md (Step 2) to 'Inspect the PDF first' and the script scripts/remove_text_watermark.py (Line 39) uses pypdf.PdfReader to load the file.
  • Boundary markers: There are no boundary markers or instructions telling the agent to treat the PDF content as data only and ignore embedded instructions.
  • Capability inventory: The skill has file system access (read/write) through the scripts/remove_text_watermark.py script.
  • Sanitization: There is no sanitization or filtering of the PDF content before the agent evaluates it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:58 AM
Security Audit — agent-trust-hub — pdf-watermark-remover