composer-dependencies
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow relies on fetching and interpreting external changelogs and upgrade guides, creating a surface for potential injection of instructions via third-party documentation.
- Ingestion points: External web search results for package changelogs and user-provided release notes (SKILL.md, references/update-workflow.md).
- Boundary markers: The skill does not define specific delimiters or warnings to prevent the agent from obeying instructions that might be embedded within the retrieved changelog text.
- Capability inventory: The playbook assumes the agent has access to execute shell commands (
composer,git,phpunit,phpstan) and modify sensitive project configuration files (composer.json,composer.lock). - Sanitization: The instructions do not specify any validation or filtering of the external content before it is processed by the agent to determine the update steps.
Audit Metadata