forge-performance

Warn

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a Node.js script using the command node ../../../.fullstack-forge/runtime/cli/src/composition-entry.js. Running local scripts via relative path traversal outside the skill's directory is a security risk.
  • [PROMPT_INJECTION]: The skill contains a directive to "Read the canonical playbook now and follow it exactly" from a relative path (../../../.fullstack-forge/skills/forge-performance/SKILL.md). This allows external content to override or dictate agent behavior.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. It ingests data from external files including a canonical SKILL.md and .forge/composition.json. The skill's capabilities include shell command execution via Node.js. It lacks explicit boundary markers or sanitization logic to handle potentially malicious instructions within these ingested files.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 6, 2026, 06:48 PM
Security Audit — agent-trust-hub — forge-performance