insforge-backend-advisor
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and act upon the output of backend diagnostic scans which may contain attacker-influenced recommendations or descriptions.
- Ingestion points: Processes JSON output from
npx @insforge/cli diagnose advisor --jsonas described inSKILL.md. - Boundary markers: The instructions explicitly warn the agent: "confirm the affected object's actual state before recommending a change — do not blindly apply advisor's recommendation."
- Capability inventory: The agent has the capability to execute shell commands and arbitrary SQL queries using the
@insforge/clitool. - Sanitization: There is no automated sanitization of the diagnostic output; the skill relies on instructional guardrails.
- [COMMAND_EXECUTION]: Instructs the agent to execute various system and database management commands using the
@insforge/cli, including running ad-hoc SQL queries and inspecting security policies. - [EXTERNAL_DOWNLOADS]: Uses
npxto download and execute the@insforge/clipackage from the npm registry. This is the official command-line interface provided by the vendor for project management.
Audit Metadata