plan-writing
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No attempts to override system instructions or bypass safety filters were detected. The skill uses instructional language consistent with its stated purpose of improving task planning.
- [Data Exposure & Exfiltration] (SAFE): There are no patterns suggesting the access of sensitive files (like SSH keys or credentials) or the exfiltration of data via network requests.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download or execute remote code. References to commands like
npm installare used within examples of how to write specific plans and are not executed by the skill itself. - [Obfuscation] (SAFE): No encoded strings, zero-width characters, or homoglyphs were found in the content.
- [Indirect Prompt Injection] (SAFE): The skill does not ingest untrusted external data (e.g., from APIs or web scraping). It serves as a static set of guidelines for the agent's internal reasoning process.
Audit Metadata