ble-gatt
GATT service/characteristic enumeration on BLE peripherals, unauthenticated read/write exploitation, pairing downgrade to Just Works, and over-the-air sniffing with Sniffle or Ubertooth. Covers firmware update channels, hidden debug services, and missing auth on sensitive characteristics.
69
85%
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
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 guide that provides step-by-step instructions for unauthenticated GATT enumeration, credential harvesting, pairing downgrade/MITM, firmware/OTA writes, sniffing, and address spoofing—clearly facilitating unauthorized access and abuse.
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 prints, stores, and adds raw characteristic values and device identifiers (e.g., val.hex(), value_hex, TARGET = "AA:BB:CC:DD:EE:FF") into files and a knowledge-graph node, which requires the agent to handle and emit secret/credential values verbatim.
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 skill repeatedly instructs the user/agent to run privileged commands (sudo hcitool/bettercap/btmgmt, adapter bdaddr spoofing and flashing firmware) which require elevated privileges and can change host network/adapter state, so it encourages actions that modify the machine state.
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
This skill’s runtime workflow performs BLE discovery and full GATT dumping by connecting to arbitrary nearby devices (e.g., via `bleak`/`gatttool`), and the returned GATT “Value”/characteristic data becomes readable text injected into the agent’s context; the outsider free-text source is the content extracted from those external devices’ advertisements/characteristics at runtime.
- 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.