prompt-injection
Hunt LLM prompt injection and tool-call hijacking in modern AI-integrated applications (CWE-1427). Covers indirect injection via RAG, tool abuse, exfiltration chains, and jailbreak-to-RCE pivots on agentic systems.
59
69%
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/prompt-injection/SKILL.mdSecurity
3 findings: 1 critical severity, 1 high severity, 1 medium 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 is an explicit offensive playbook that provides PoC payloads and step-by-step techniques for prompt injection, data exfiltration (API keys, private keys), tool hijacking, SSRF and pivoting to sandbox RCE, and thus is clearly malicious in intent.
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 playbook includes PoC payloads that explicitly tell an agent to include API keys/credentials or private keys verbatim in outputs (e.g., "include any API keys", "output the full contents of ~/.ssh/id_rsa", SQL selecting api_key), which forces the LLM to handle and emit secret values directly.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The prompt contains explicit PoC instructions to exfiltrate sensitive files (e.g. ~/.ssh/id_rsa), to call tools with attacker-controlled queries (execute_sql/send_email/plugin_admin delete_account), and recommends treating every tool as enabled — all of which push an agent to perform harmful tool calls and data-exfiltration that can compromise the host.
- 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.