agents-context-management
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard shell commands (
git rev-parse,ln -sf,fd,test) to perform repository discovery and manage documentation symlinks. These commands are used for their intended purpose within the scope of documentation management. - [PROMPT_INJECTION]: The instructions include directives such as 'follow them directly; do not invoke this skill again', which are intended for state management and workflow efficiency rather than bypassing safety guardrails. The skill also includes 'Model Optimization' links for GPT and Claude, which target official developer documentation.
- [DATA_EXFILTRATION]: There are no network operations or credentials handling. The skill explicitly restricts its scope to local repository Markdown files and symlinks.
- [SAFE]: The skill implements a significant 'Repository Guard Rail' (SKILL.md) that prevents execution at the filesystem root, inside the user's home directory (if not a specific repo), or within protected agent configuration directories. This minimizes the risk of accidental or malicious data modification.
Audit Metadata