skills/hhu3637kr/skills/spec-test/Gen Agent Trust Hub

spec-test

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection (Category 8) because it is instructed to read and process documentation files that may be influenced by external or untrusted sources.
  • Ingestion points: The skill reads multiple files including exploration-report.md, plan.md, and summary.md to inform its testing tasks.
  • Boundary markers: No specific delimiters or "ignore previous instructions" warnings are provided to prevent the agent from obeying instructions embedded within these files.
  • Capability inventory: The skill can write markdown files (test-plan.md, test-report.md) and send internal messages to other roles (TeamLead, spec-writer, spec-debugger). It lacks more dangerous capabilities like arbitrary command execution or network access.
  • Sanitization: The instructions do not include steps to sanitize or validate data extracted from the ingested files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 07:21 AM