skills/jr2804/prompts/etsi-spec/Gen Agent Trust Hub

etsi-spec

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses uv run to execute a local Python script scripts/get_etsi_spec.py. This is a standard execution pattern for this environment and is limited to running the provided script with user-supplied specification numbers as arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by downloading and parsing PDF files from etsi.org to extract titles and publication dates.
  • Ingestion points: The extract_pdf_metadata function in scripts/get_etsi_spec.py downloads PDFs from ETSI and extracts text from the first page using PyPDF2.
  • Boundary markers: None identified. The extracted text is directly printed to the console.
  • Capability inventory: The skill has network access (via requests) to download PDFs and file system access (via uv run) to execute the script.
  • Sanitization: The script performs basic regex filtering on extracted text to identify titles, but does not sanitize for potentially malicious instructions embedded in the PDF content. However, the risk is low as the output is primarily for user display.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 04:00 PM