forge-infrastructure
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Node.js script located at
../../../.fullstack-forge/runtime/cli/src/composition-entry.jsusing the system'snodeinterpreter to perform 'runtime composition'. - [PROMPT_INJECTION]: This skill functions as an 'adapter' that redirects the agent to load instructions from a canonical playbook file (
../../../.fullstack-forge/skills/forge-infrastructure/SKILL.md) and additional paths specified in a local configuration file (.forge/composition.json). This pattern creates an indirect prompt injection surface where the agent's behavior is determined by data in the local environment. - Ingestion points:
.forge/composition.json(local file),../../../.fullstack-forge/skills/forge-infrastructure/SKILL.md(external file relative to skill directory). - Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore potential commands within the loaded composition data.
- Capability inventory: File system read access and shell command execution via
node. - Sanitization: No evidence of sanitization or validation of the paths or content provided by the composition JSON or canonical playbook.
Audit Metadata