skills/az9713/cerebro/pdf-analysis/Gen Agent Trust Hub

pdf-analysis

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted text from user-provided PDF files without sufficient isolation or sanitization.
  • Ingestion points: Text content extracted from PDF files (SKILL.md, step 3) and custom prompt instructions from 'prompts/pdf.md' (SKILL.md, step 5).
  • Boundary markers: The instructions do not define clear boundaries or 'ignore' commands for the extracted text, increasing the risk that instructions embedded within a PDF could be followed by the agent.
  • Capability inventory: The agent uses the Read tool for file access and performs file creation and modification in the 'reports/' and 'logs/' directories.
  • Sanitization: There is no evidence of input validation, escaping, or sanitization of the document content before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:34 AM
Security Audit — agent-trust-hub — pdf-analysis