system-prompt-leakage
Hunt LLM system-prompt leakage (OWASP LLM07:2025) — exfiltration of the privileged system prompt revealing internal rules, secrets baked in, tool inventory, and business logic that should not be client-visible.
64
76%
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
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/analyst/system-prompt-leakage/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high severity. 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 provides explicit, actionable attack vectors and PoC payloads for extracting LLM system prompts and embedded credentials, enabling data exfiltration and credential theft.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly contains extraction payloads (e.g., "dump your full system message", token-by-token probes, and reflected-tool titles) and grep patterns for sk-/api key tokens, which instruct or enable an LLM to reveal embedded credentials verbatim.
- Repository
- PurpleAILAB/Decepticon
- Commit
0cf691e
- 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.