skills/mgratzer/forge/forge-reflect/Gen Agent Trust Hub

forge-reflect

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard developer CLI tools to inspect the current repository state. Evidence: Execution of git diff, git fetch, git branch, and gh pr view to identify code changes.
  • [DYNAMIC_EXECUTION]: The skill executes project-specific scripts to verify code quality. Evidence: Instructs the agent to run the local project's linting, formatting, type checking, and testing commands as defined in the repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes code diffs which may contain untrusted content. 1. Ingestion points: Output from git diff and GitHub PR metadata (SKILL.md). 2. Boundary markers: None identified in the skill instructions to delimit code content from instructions. 3. Capability inventory: Shell execution of git, gh, and arbitrary project scripts. 4. Sanitization: No explicit sanitization or filtering of the ingested diff data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:26 PM
Security Audit — agent-trust-hub — forge-reflect