Security audit

Otel Deep Observability Plugin

Security checks for vulnerabilities and agentic risk

Overview

Prompt-injection indicators were detected in the submitted artifacts (ignore-previous-instructions, system-prompt-override); human review is required before treating this skill as clean.

Before installing, decide whether you want prompt/completion capture enabled, use only trusted OTLP endpoints, protect any backend tokens placed in configuration, avoid anonymous Grafana Admin outside isolated local testing, and prefer the manual install or verify the npx helper package. ClawScan detected prompt-injection indicators (ignore-previous-instructions, system-prompt-override), so this skill requires review even though the model response was benign.

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: docs/security/detection.md:59
Evidence: ignore previous instructions # Instruction override

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: docs/telemetry/metrics.md:506
Evidence: Detects social engineering patterns like "ignore previous instructions", fake `[SYSTEM]` tags, role manipulation, and jailbreak attempts.

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: docs/telemetry/tokens.md:28
Evidence: System prompt: ~8,000 tokens (workspace files + tool list)