skills/phpstan/tally/tally-rewind/Gen Agent Trust Hub

tally-rewind

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/measure.sh script downloads the phpstan/tally tool using composer. This is an official tool provided by the skill author to enable the benchmarking functionality.
  • [COMMAND_EXECUTION]: The skill utilizes several CLI tools including git for history traversal, composer for dependency management, and gh for interacting with GitHub. It also allows users to provide an optional setup command via the TALLY_REWIND_PREPARE environment variable to configure the project environment before benchmarking.
  • [DYNAMIC_EXECUTION]: The benchmarking script dynamically generates a PHP configuration file (.tally-rewind.php) at runtime to configure the Tally execution environment and project autoloaders.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes potentially untrusted data from git commit messages, changelogs, and pull request descriptions to identify historical performance improvements.
  • Ingestion points: Commit messages (git log), pull request metadata (gh), and project changelog files.
  • Boundary markers: The agent is instructed to parse these for specific keywords and semantic meaning related to performance, rather than executing them as instructions.
  • Capability inventory: The skill possesses capabilities to execute shell commands and PHP code through its benchmarking scripts.
  • Sanitization: No specific sanitization is performed on the ingested text beyond the LLM's natural language processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 02:15 PM