absurdist-readme-writer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to process external repository content (Instruction 1) to generate its output. This creates an ingestion surface for untrusted data. However, the skill's capabilities are limited to text generation and display, without tools for network exfiltration, file system modification, or command execution, which limits the potential impact. \n- Ingestion points: Instruction to 'understand the repository’s purpose' (SKILL.md). \n- Boundary markers: None identified. \n- Capability inventory: Display and text generation only; no hazardous capabilities found. \n- Sanitization: None identified.
Audit Metadata