read-bin-docs

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill is highly vulnerable to indirect prompt injection through malicious PDF content. Ingestion points: scripts/extract_pdf_text.py accepts and processes untrusted PDF files via PdfReader. Boundary markers: Absent. The script extracts raw text and concatenates it without any delimiters or 'ignore instructions' warnings. Capability inventory: The script includes the ability to write extracted content to the local filesystem using the --output argument, which can be exploited if an injected instruction directs the agent to overwrite sensitive files. Sanitization: Absent. No filtering or validation is performed on the extracted text before it is returned to the agent or written to a file.
  • Unverifiable Dependencies (LOW): Relies on the external pypdf library. While pypdf is a standard package, it is a third-party dependency that must be installed locally.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 06:55 AM