skills/yansfil/harness-camp/specify/Gen Agent Trust Hub

specify

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to create directories for specifications (mkdir -p specs/{name}). This is a restricted and legitimate use of shell commands for project organization.
  • [PROMPT_INJECTION]: The skill processes data from the local codebase during the research phase. While this presents an indirect prompt injection surface, the risk is mitigated by multiple user approval gates where the generated content is reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 06:24 AM