skills/maroffo/claude-forge/score/Gen Agent Trust Hub

score

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes make check and make test-e2e via the Bash tool. This is the primary functionality intended to provide a project readiness score.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8):
  • Ingestion points: Reads local file rules/quality-gates.md and the output of executed shell commands.
  • Boundary markers: Absent; there are no delimiters used to isolate potentially untrusted project data from the agent's instructions.
  • Capability inventory: The skill has access to the Bash tool for command execution.
  • Sanitization: No validation or sanitization is performed on the ingested file content or command output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 04:29 AM
Security Audit — agent-trust-hub — score