requirement-analyzer

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user data as part of its primary analysis workflow, creating a potential surface for indirect prompt injection (Category 8). \n
  • Ingestion points: The skill explicitly instructs the agent to read and understand 'preliminary requirement materials' (e.g., meeting minutes, competitor analysis) provided by the user in the '前置准备' (Preparation) section of SKILL.md. \n
  • Boundary markers: There are no specified delimiters or instructions to treat external content as data only, nor are there warnings to ignore embedded agent instructions within that content. \n
  • Capability inventory: The skill allows the agent to read local files and write generated documentation to a local directory defined by the output_dir parameter. \n
  • Sanitization: The methodology does not include steps for sanitizing or validating the input data before it is incorporated into the structured analysis templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 05:36 AM