Skills
skills/alexander-danilenko/cortex-ai-skills/agents-md-pro/Gen Agent Trust Hub

agents-md-pro

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting untrusted project data.
  • Ingestion points: The CREATE and UPDATE workflows in references/workflows.md instruct the agent to read package.json, README.md, config files, and source code.
  • Boundary markers: No delimiters or guardrail instructions are specified for processing these files to prevent the agent from following instructions embedded in the codebase.
  • Capability inventory: The skill includes the capability to write and overwrite AGENTS.md files in the local repository.
  • Sanitization: There are no instructions to sanitize or validate extracted content before it is incorporated into the generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 03:55 PM