typo3-upgrade-closure
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data during its verification workflow, which could potentially contain malicious instructions.\n
- Ingestion points: The agent fetches and processes HTTP responses, normalized DOM trees, and TYPO3 backend content (e.g., in
http-dom-proof,visual-proof, andbackend-operationsnodes defined inSKILL.md).\n - Boundary markers: The skill defines a strict worker protocol for node input/output in
SKILL.md, but does not specify explicit delimiters or "ignore" instructions for the site content being analyzed.\n - Capability inventory: The skill utilizes the
t3uCLI tool andtypo3-playwrightto interact with the environment and writes evidence artifacts to the local filesystem.\n - Sanitization: There is no mention of sanitizing or escaping the HTML/DOM content before it is processed or included in evidence logs.
Audit Metadata