qa-plan

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted data from story and design files.
  • Ingestion points: The skill reads and extracts information from files at paths such as production/epics//story-.md and design/gdd/ to build its plan.
  • Boundary markers: There are no specified delimiters or explicit instructions to the agent to disregard any commands or behavior-overriding text that might be embedded within the story files or GDDs.
  • Capability inventory: The skill uses file system tools (Read, Glob, Grep, Write) and interactive tools (AskUserQuestion) which provide a functional surface that could be misused if an injection occurs.
  • Sanitization: The skill does not perform validation or sanitization on the text extracted from input files before using it to generate the final QA plan document.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:28 PM