update-claude-md
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate repository maintenance by auditing orientation files against recent code changes. It explicitly forbids accessing global user configurations (~/.claude/CLAUDE.md).
- [COMMAND_EXECUTION]: The instructions utilize standard, well-known development tools including
git(for diffs and logs),ripgrep(rg) for searching code, and the GitHub CLI (gh) for checking PR status. These tools are used appropriately within the scope of the local repository. - [DATA_EXFILTRATION]: No unauthorized data exfiltration patterns were identified. External interaction via the GitHub CLI (
gh) targets a well-known and trusted service for project-related status checks. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository (code and diffs) to update documentation. This presents a potential surface for indirect prompt injection if an attacker embeds instructions in code comments; however, this is inherent to the skill's primary function of summarization and is considered a low risk.
Audit Metadata