founder-cognitive-boundary
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown-based instructions and JSON test prompts. There are no executable scripts, binaries, or configuration files present in the skill package.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found. The skill operates as a high-level cognitive framework for identifying leadership bottlenecks.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided descriptions of organizational problems. While it lacks specific delimiters for untrusted data, it possesses no dangerous capabilities such as network access, file system writes, or subprocess execution that would permit exploitation via indirect injection.
Audit Metadata