skills/astro-han/pawwork/office-pdf/Gen Agent Trust Hub

office-pdf

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands (mkdir, cp, uv run) to prepare a working directory and execute Python-based PDF parsing scripts. These commands are used for environment setup and task execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external PDF files provided at runtime to extract text or tables. This creates a surface where malicious instructions embedded in a PDF could influence the agent's behavior.
  • Ingestion points: External PDF files processed via pdfplumber and pypdf as described in SKILL.md.
  • Boundary markers: None identified; extracted text is printed directly to standard output.
  • Capability inventory: The skill uses shell commands and uv run to execute Python code, which can perform filesystem operations within the work/ directory.
  • Sanitization: No explicit sanitization or filtering of the extracted text is performed before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 07:24 PM
Security Audit — agent-trust-hub — office-pdf