problem-framing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest untrusted user input and process it into a structured format using a writing tool. Ingestion points: User input gathered in 'Step 1: Gather Raw Input' within SKILL.md. Boundary markers: Absent; the prompt does not instruct the agent to ignore instructions embedded in the user's idea. Capability inventory: 'Write tool' used to save data to 'design/01-problem-framing.md'. Sanitization: Absent; input is reflected into the final document without filtering.
- Prompt Injection (SAFE): No malicious override or bypass patterns detected in the instructions.
- Data Exposure & Exfiltration (SAFE): No sensitive file access or non-whitelisted network operations found.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not execute code or download external packages.
Audit Metadata