implement-plus

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests ticket descriptions and comments from external sources like GitHub and Linear to guide its implementation tasks. This creates a surface for indirect prompt injection where malicious instructions in a ticket could influence the agent's behavior.
  • Ingestion points: Ticket body and comments retrieved via GitHub 'gh' or Linear MCP (SKILL.md).
  • Boundary markers: The skill does not define clear delimiters or specific instructions to ignore embedded commands within the fetched ticket content.
  • Capability inventory: The agent has the ability to execute shell commands (PHP, Composer, Git) and spawn sub-agents for code review (SKILL.md).
  • Sanitization: No sanitization or filtering is applied to the untrusted ticket data before it is incorporated into the agent's context.
  • [COMMAND_EXECUTION]: The skill executes standard PHP and Laravel commands including 'php artisan test', 'composer analyse', 'vendor/bin/pest', 'vendor/bin/pint', and 'git'. These operations are consistent with the skill's primary purpose of software development.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 07:39 PM
Security Audit — agent-trust-hub — implement-plus