data-and-model-poisoning
Hunt LLM training-data and model poisoning (OWASP LLM04:2025) — adversarial inputs that bias future model behaviour through fine-tuning, RLHF, or continuous-learning loops.
73
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This document contains explicit, actionable instructions and proof-of-concept payloads for LLM data/model poisoning (triggered backdoors, RAG persistence, self-judge collapse, embedding poisoning), indicating deliberate malicious guidance.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
SKILL.md describes an audit workflow whose focus is on public-facing free-text feedback, thumbs up/down, and “feedback documents” that can be ingested into RLHF/DPO or RAG corpora; if such workflow is implemented, it would ingest outsider-authored user feedback content at runtime into the training/RAG context.
- Repository
- PurpleAILAB/Decepticon
- Commit
e34afba
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.