backend-engineering
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill contains a 'Companion check' directive that instructs the agent to execute a directory listing command (
ls) on specific local filesystem paths (e.g.,~/.claude/skills/,~/.agent/skills/) to determine if recommended auxiliary skills are already present. - [EXTERNAL_DOWNLOADS]: Upon identifying missing companion tools, the skill suggests that the user install additional modules from the 'AbsolutelySkilled' vendor using the
npxcommand line utility. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze technical data provided by the user, such as database schemas and API specifications. While it lacks explicit boundary markers or specific sanitization instructions for this untrusted content, the risk is mitigated by its primary function as an advisory tool for engineering trade-offs.
Audit Metadata