typo3-initial-release

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute various shell commands to manage the release workflow, including git tag, composer validate, and searches using rg (ripgrep) and find for code and documentation patterns.- [PROMPT_INJECTION]: The skill processes untrusted content from the extension repository to determine release readiness and documentation updates, which could be exploited via indirect prompt injection.
  • Ingestion points: Reads composer.json, README.md, CHANGELOG.md, and various files within the Documentation/ directory.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ingested files are present in the skill definition.
  • Capability inventory: The skill utilizes shell commands (ddev, git, composer) and executes local repository scripts.
  • Sanitization: There is no mention of sanitizing or validating the data read from the repository before it influences agent behavior.- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to run scripts located within the local repository, such as Build/Scripts/runTests.sh, scripts/validate_docs.sh, and scripts/render_docs.sh. If these repository-provided scripts are malicious, they could execute arbitrary code in the environment where the agent is running.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 07:25 AM
Security Audit — agent-trust-hub — typo3-initial-release