typo3-batch
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted local data from a codebase to perform complex refactoring tasks.
- Ingestion points: As described in the "Research" and "Common TYPO3 Batch Operations" sections of SKILL.md, the agent scans local files including PHP classes, TCA configurations, Fluid templates, and SQL files.
- Boundary markers: The instructions lack specific delimiters or warnings to prevent the agent from following instructions that might be embedded within the comments or strings of the code being analyzed.
- Capability inventory: The skill utilizes the agent's environment to execute php -l, composer normalize, and run test suites (PHPUnit/Functional tests).
- Sanitization: There is no evidence of sanitization or filtering applied to the code content before it is processed by the agent's logic.
- [COMMAND_EXECUTION]: The skill requires the execution of shell commands on the local system for code validation.
- Evidence: The "Verification Checklist" in SKILL.md mandates running php -l and composer normalize. The "Execution Rules" also mention running PHPStan and relevant tests after applying changes to a unit.
Audit Metadata