release-it
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed entirely of markdown documentation files (
SKILL.md,release-it.md,release-it.mini.md,release-it.nano.md) providing engineering guidelines. It contains no shell scripts, Python code, or other executable artifacts. - [PROMPT_INJECTION]: No malicious injection patterns or safety bypass attempts were detected. The authoritative tone used in the documentation (e.g., "OBEY", "Primary Directive") is strictly limited to defining engineering policies for software reliability and does not target agent safety constraints.
- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or exfiltration patterns were found. The engineering rules specifically include instructions to "not log secrets" and to treat all external input as untrusted.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any network operations, download external scripts, or execute remote code.
- [INDIRECT_PROMPT_INJECTION]: While the skill discusses the handling of external data, it does not provide an automated ingestion surface. Instead, it provides defensive instructions (e.g., "Validate external responses") which mitigate injection risks in the software being designed.
Audit Metadata