advanced-prompting

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill provides 'Reset Prompts' that instruct the AI to ignore or disregard its previous context or instructions. Evidence in references/reset-prompts.md: 'Forget everything we've discussed. I need [core requirement].' Evidence in SKILL.md: 'Scrap this and implement the elegant solution'. These patterns are used here for user-controlled context management but align with known override techniques.
  • [NO_CODE]: The skill consists entirely of Markdown files providing guidance and prompt examples. It does not include any executable code, scripts, or dependency manifests.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:20 PM
Security Audit — agent-trust-hub — advanced-prompting