specsfy-specialist-laravel-package-manager
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute various
composerCLI commands (e.g.,composer require,composer show,composer validate, andcomposer dump-autoload). These commands are essential for its primary purpose as a package manager and include validation steps to ensure manifest integrity. - [EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of external PHP packages from GitHub and the Composer registry (Packagist). It implements a safety check by requiring the AI to normalize URLs to a strict format (lowercase, numbers, specific symbols) and to verify that the target repository contains a compatible Composer manifest before installation.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it ingests data from external GitHub repositories to generate local documentation and installation instructions.
- Ingestion points: External GitHub repository manifests (
composer.json) and documentation (README.md) as specified inSKILL.md(Steps 3 and 4). - Boundary markers: The skill instructs the agent to normalize input URLs and identify specific structured fields, but does not provide explicit prompt delimiters for the ingested content.
- Capability inventory: File writes to
docs/packages/and shell command execution via thecomposertool. - Sanitization: The skill mandates the use of
composer validate --strictand warns against executing post-installation scripts without manual verification of their purpose.
Audit Metadata