typo3-typoscript-ref

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/fetch-docs.sh script downloads TYPO3 documentation files from official, well-known GitHub repositories (github.com/TYPO3-Documentation and github.com/TYPO3). These downloads are used to populate the skill's local reference cache and are consistent with the skill's stated purpose of providing documentation lookups.
  • [COMMAND_EXECUTION]: The skill uses several local scripts to perform its tasks. scripts/lookup.sh acts as the main entry point, calling scripts/detect-version.sh to determine the project's TYPO3 version from composer.lock or composer.json using Python, and scripts/fetch-docs.sh to manage documentation. These operations are standard for a developer utility tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (official TYPO3 documentation repositories). This establishes an attack surface for indirect prompt injection.
    • Ingestion points: scripts/fetch-docs.sh fetches remote .rst files from GitHub and saves them as Markdown in a local cache/ directory.
    • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the processed documentation files.
    • Capability inventory: The skill executes local shell and Python scripts via the Bash tool to perform lookups and updates.
    • Sanitization: The scripts/rst2md.py script performs structural conversion of documentation but does not include semantic sanitization to filter out potential prompt injection attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 09:27 AM