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

pdf

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for environment setup and PDF processing.
  • Evidence: Use of uv pip install, python3 -m pip install, brew install, sudo apt-get install, and pdftoppm in SKILL.md.
  • [PRIVILEGE_ESCALATION]: The skill requests administrative privileges to install system-level utilities.
  • Evidence: sudo apt-get install -y poppler-utils in SKILL.md. This is a standard procedure for installing the well-known Poppler rendering tool on Debian-based systems.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external PDF files, which represents an attack surface for indirect prompt injection if the ingested content contains instructions designed to influence the agent.
  • Ingestion points: pdfplumber and pypdf are used to extract text and data from PDF files.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.
  • Capability inventory: The skill has capabilities for shell command execution (pdftoppm), file system writes (output/pdf/), and package installation.
  • Sanitization: No explicit sanitization or validation of extracted text is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:46 PM
Security Audit — agent-trust-hub — pdf