skills/letta-ai/skills/pdf/Gen Agent Trust Hub

pdf

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands such as pdftoppm for PDF rendering and various package managers (uv, pip, brew, apt-get) for environment setup.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of several external Python packages (reportlab, pdfplumber, pypdf) and system-level utilities (poppler). While these are well-known tools, they involve downloading and executing code from external repositories.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its primary purpose is to process external PDF data which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: External PDF files read and rendered via pdfplumber, pypdf, and pdftoppm in SKILL.md.
  • Boundary markers: Absent; the skill lacks explicit instructions or delimiters to isolate content from the PDF from the agent's system instructions.
  • Capability inventory: The agent has the ability to write to the file system (output/pdf/), execute system commands (pdftoppm), and install new software packages.
  • Sanitization: No sanitization or validation of the PDF content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 04:37 AM