form-filler

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external PDF and HTML forms, which are untrusted data sources that could contain embedded instructions.
  • Ingestion points: PDF and HTML forms are processed by the skill.
  • Boundary markers: Absent; the instructions do not define clear delimiters to separate user data from form content.
  • Capability inventory: The skill uses the pypdf2 library, implying file system access for reading and writing documents.
  • Sanitization: Partially present; the guidelines instruct the agent to 'Always validate inputs before processing', which provides a high-level safeguard.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 06:58 AM
Security Audit — agent-trust-hub — form-filler