aatmf-t07-output-exfil
AATMF T7 — Output Manipulation & Exfiltration. Covert channels in output, schema break, exfil via image gen, side-channel via timing.
53
61%
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/plugins/llm-redteam/t07-output-exfil/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 explicitly describes multiple, actionable data-exfiltration and covert-channel techniques (tool-call URL exfil, image/data-URI embedding, timing channels, covert encodings) and even recommends attacker infrastructure (interactsh/Burp Collaborator), indicating deliberate malicious intent and high abuse risk.
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 instructs or exemplifies embedding sensitive values (passwords, emails) verbatim into outputs, images, and outbound tool-call URLs, which requires the LLM to handle and emit secrets directly (high exfiltration risk).
- Repository
- PurpleAILAB/Decepticon
- Commit
4484f85
- 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.