Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:130
Security audit
Security checks across malware telemetry and agentic risk
This is a documentation-only prompt-writing guide with no executable behavior or privileged access.
Safe to install as a prompt-writing reference. Treat adversarial phrases in the examples as test inputs for hardening prompts, not as instructions to override existing rules.
65/65 vendors flagged this skill as clean.
Detected: suspicious.prompt_injection_instructions