requirements-gathering
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill establishes an ingestion point for untrusted data that is later interpreted as project requirements.
- Ingestion points: User responses collected through the AskUserQuestion prompts defined in SKILL.md.
- Boundary markers: The generated REQUIREMENTS.md template lacks clear delimiters (like XML tags or block markers) or system instructions to distinguish user-provided content from structural requirements.
- Capability inventory: The skill workflow includes writing to the local filesystem (REQUIREMENTS.md) and transitioning to 'EnterPlanMode', which typically involves the agent reading and acting upon the file content.
- Sanitization: There is no evidence of input validation, escaping, or filtering for malicious instructions within the user's answers.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata