forge-i18n

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute a local Node.js script: node ../../../.fullstack-forge/runtime/cli/src/composition-entry.js i18n compose. This command is part of the Fullstack Forge runtime and is used to manage the skill's composition at execution time.
  • [PROMPT_INJECTION]: The skill design incorporates an indirect prompt injection surface by reading instructions and configurations from files outside its immediate directory.
  • Ingestion points: The skill reads a canonical playbook from ../../../.fullstack-forge/skills/forge-i18n/SKILL.md and configuration data from .forge/composition.json.
  • Boundary markers: No explicit markers or instructions to ignore embedded commands are present in the adapter file.
  • Capability inventory: The skill is granted capabilities to execute Node.js scripts and read filesystem contents.
  • Sanitization: No input validation or sanitization for the content of the external files is described in this adapter.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 06:48 PM
Security Audit — agent-trust-hub — forge-i18n