essay-revise
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Prompt Injection (SAFE): The instructions establish a professional persona and task boundaries without using override or bypass patterns.
- Data Exposure & Exfiltration (SAFE): The skill references local files like essay-brief.md and essay-draft.md, which are relevant to its stated purpose. There are no network capabilities or hardcoded credentials detected.
- Indirect Prompt Injection (SAFE): The skill processes untrusted data (user-provided text and notes) but lacks any capabilities to execute commands or exfiltrate data. Evidence Chain: 1. Ingestion points: essay-brief.md, essay-draft.md, and user-provided sections. 2. Boundary markers: Absent. 3. Capability inventory: None. 4. Sanitization: Absent.
- No Code (SAFE): No executable code, scripts, or package dependencies are present in the skill definition.
Audit Metadata