typo3-extension-upgrade
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process third-party code (TYPO3 extensions), creating an inherent surface for indirect prompt injection if the scanned code contains malicious instructions targeted at the agent.
- Ingestion points: The
scripts/scan-deprecations.shscript (line 19) and automated tools like Rector and Fractor (SKILL.md lines 19-20) read and analyze the entire source code of a TYPO3 extension. - Boundary markers: None explicitly defined. The skill does not instruct the agent to use specific delimiters when processing the extension's code files.
- Capability inventory: The skill possesses the capability to execute shell commands for scanning (
grep) and running refactoring tools that modify the local file system. - Sanitization: The skill relies on the standard parsing logic of established development tools (Rector, PHPStan, Fractor) to handle input files.
Audit Metadata