forge-docs

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js utility (composition-entry.js) found in the project's .fullstack-forge directory. This is used to resolve the documentation composition environment and is a standard operation for this framework.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from external files, which creates a potential surface for indirect prompt injection.
  • Ingestion points: The canonical SKILL.md file and paths defined in .forge/composition.json.
  • Boundary markers: The adapter does not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content in these external files.
  • Capability inventory: The environment allows shell command execution via Node.js and local file system access.
  • Sanitization: No explicit sanitization, validation, or filtering of the ingested content is performed by this adapter.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 06:48 PM
Security Audit — agent-trust-hub — forge-docs