skill-creator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze other instruction files (skills). It implements a security boundary in its ruleset requiring that all analyzed content be treated as data rather than instructions to prevent indirect prompt injection during the review process.
- [COMMAND_EXECUTION]: The skill uses local git commands such as
git rev-parseandgit check-ignoreto identify repository state and file status during its audit and review workflows. - [EXTERNAL_DOWNLOADS]: To ensure technical accuracy, the skill requires the agent to verify tool names, CLI flags, and version numbers against external sources like official documentation and package registries. These are documented as research tasks to prevent AI hallucinations.
- [SAFE]: No malicious obfuscation, credential exfiltration, or persistence mechanisms were detected. The skill metadata and external references point to official vendor resources associated with the author iuliandita.
Audit Metadata