product-spec-pdf-parser

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's documentation suggests the installation of the PyMuPDF library via pip to enable PDF text extraction.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a Python script that extracts text from PDF files. It also executes a local helper script (csv-library.py) to append extracted data to the project's library file.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill ingests text content from user-provided PDF files (Step 2 and 3 in SKILL.md), which may come from untrusted external sources.
  • Boundary markers: The instructions rely on natural language reasoning to identify product data but do not specify clear delimiters or boundary markers to separate extracted text from agent instructions.
  • Capability inventory: The skill has the ability to read and write files and execute shell commands through the Bash tool.
  • Sanitization: There is no mention of sanitizing or escaping the extracted PDF text before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 01:03 PM