writing-agent-rules

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown documentation providing best practices for writing agent-facing rules. No security issues were detected across the analyzed threat categories.
  • [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were found. The instructions are meta-instructional and intended for the agent to follow when generating documentation.
  • [DATA_EXFILTRATION]: There are no network operations (e.g., curl, wget) or access to sensitive local file paths (e.g., .ssh, .aws) that could lead to data exfiltration.
  • [REMOTE_CODE_EXECUTION]: The skill does not perform any external package installations or execute remote scripts.
  • [COMMAND_EXECUTION]: No shell commands or subprocess calls are present in the documentation.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or private tokens are present. The text actually warns against secret exposure under its 'Hard invariant' section.
  • [NO_CODE]: The skill contains only instructional text and metadata, with no scripts or executable logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 05:04 PM
Security Audit — agent-trust-hub — writing-agent-rules