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 scriptscripts/remove_text_watermark.py(Line 39) usespypdf.PdfReaderto 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.pyscript. - Sanitization: There is no sanitization or filtering of the PDF content before the agent evaluates it.
Audit Metadata