enhance-agent-prompts
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a static analyzer for markdown files. It defines 30 specific patterns to evaluate prompt effectiveness and security (e.g., verifying tool restrictions like restricted Bash commands).
- [PROMPT_INJECTION]: While the skill contains text related to prompt engineering, it does not contain instructions to bypass safety filters or override agent behavior. Its primary purpose is to strengthen prompt constraints.
- [COMMAND_EXECUTION]: The skill mentions command-line tools like 'git' and 'npm' within its documentation for 'Tool Configuration' advice, but it does not execute arbitrary shell commands itself. The JavaScript argument parsing is limited to internal configuration flags (--fix, --verbose).
- [DATA_EXFILTRATION]: The skill defines typical file locations for agents (e.g., ~/.claude/agents/) for discovery purposes but does not contain any network operations or mechanisms to exfiltrate discovered data.
- [EXTERNAL_DOWNLOADS]: There are no remote URLs, package installations, or external scripts referenced for execution.
Audit Metadata