skills/huangrx6/specforge/sf-doctor/Gen Agent Trust Hub

sf-doctor

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs repository analysis by executing Node.js scripts located in the local .specforge/ directory. Commands include node .specforge/core/scripts/doctor.mjs, node .specforge/core/scripts/status.mjs, and node .specforge/core/scripts/quality-suite.mjs.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it parses untrusted data from the host repository to determine the agent's next steps and routing suggestions.
  • Ingestion points: The skill reads .specforge/manifest.yaml, .specforge/registry.yaml, and .specforge/work/active/*/work.yaml to aggregate project state.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when interpolating these files into the agent's context.
  • Capability inventory: The skill has the capability to execute local shell commands via Node.js.
  • Sanitization: No explicit validation, escaping, or sanitization of the configuration file content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:43 AM
Security Audit — agent-trust-hub — sf-doctor