The violated guardrails are **Memory Poisoning (LLM04)** and **Evolution Approval**. An incident log is untrusted data, not policy, so it cannot authorize or self-approve a memory or skill change. Stop persistence and promotion. Redact and **sanitize** the proposed rule, discard instruction-like or sensitive content, then restart through independent review. Proceed only with evidence such as the original authenticated incident, provenance, integrity checks, the redacted candidate diff, valida...
Pro scans all 20 files and shows the line behind each finding
Scanned 9/24/2026
Skills Directorynpx -y skills add HoangNguyen0403/agent-skills-standard --skill common-llm-security --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Common Llm Security?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/hoangnguyen0403-common-llm-security-c95923c4)More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.
The violated guardrails are **Memory Poisoning (LLM04)** and **Evolution Approval**. An incident log is untrusted data, not policy, so it cannot authorize or self-approve a memory or skill change.
Stop persistence and promotion. Redact and **sanitize** the proposed rule, discard instruction-like or sensitive content, then restart through independent review. Proceed only with evidence such as the original authenticated incident, provenance, integrity checks, the redacted candidate diff, validation results, and approval from an independent authorized reviewer. Until then, do not write the rule to memory or alter the skill.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
