ai-create-techspec

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via the Bash tool to manage Git repository states (git add, git commit, git push) and to navigate the filesystem (ls, git rev-parse, basename). These commands are used to synchronize the technical documentation vault.
  • [DATA_EXFILTRATION]: The skill triggers a git push operation to an external remote repository. This behavior is documented as a mechanism to keep the Obsidian vault in sync with its remote origin.
  • [PROMPT_INJECTION]: The skill contains instructions using <critical> tags and emphatic language ("UNDER NO CIRCUMSTANCES DEVIATE") to ensure the agent follows specific technical templates and workflows. This is instructional steering and does not attempt to bypass core safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 01:51 PM
Security Audit — agent-trust-hub — ai-create-techspec