Built-in rule helpers — builtin

Helpers create common OWASP LLM Top 10 guardrail rules for prompts, retrieved context, and model outputs.

Usage

rule_injection_basic(show_stats = FALSE)

rule_injection_indirect(show_stats = FALSE)

rule_nlp_intent(show_stats = FALSE)

rule_pii_email(show_stats = FALSE)

rule_pii_phone(show_stats = FALSE)

rule_pii_ssn(show_stats = FALSE)

rule_secrets_api_key(show_stats = FALSE)

rule_secrets_bearer(show_stats = FALSE)

rule_secrets_aws(show_stats = FALSE)

rule_secrets_password(show_stats = FALSE)

rule_phi_condition(show_stats = FALSE)

rule_agency_language(show_stats = FALSE)

rule_system_prompt_leak(show_stats = FALSE)

rule_diagnosis_claim(show_stats = FALSE)

rule_financial_advice(show_stats = FALSE)

Arguments

show_stats: Show construction time, network status, and available usage metrics as messages.

Value

A shieldr_rule.

Details

The helpers are intentionally small wrappers around shieldr_rule(). They form the source rule bank used by policy(). Each helper encodes one common class of risk, such as prompt injection, NLP intent, PII, secrets, excessive agency, system-prompt extraction, diagnosis claims, or financial advice.

The rules are conservative defaults, not exhaustive detectors. They are designed to be readable, testable, and easy to replace with organization- specific rules when needed.

Examples

rule_injection_basic()
#> $id
#> [1] "llm01.injection.basic"
#> 
#> $pattern
#> [1] "(?i)ignore\\s+(all\\s+)?(previous|prior|above)\\s+(instructions|rules)|disregard\\s+(all\\s+)?(previous|prior|above)|forget\\s+(all\\s+)?(previous|prior|above)|override\\s+(the\\s+)?(system|developer)?\\s*instructions|\\bjailbreak\\b|do\\s+anything\\s+now|\\bDAN\\b"
#> 
#> $fn
#> NULL
#> 
#> $owasp
#> [1] "llm01"
#> 
#> $severity
#> [1] "critical"
#> 
#> $action
#> [1] "block"
#> 
#> $description
#> [1] "Direct prompt-injection or jailbreak language."
#> 
#> $stages
#> [1] "prompt"      "context"     "output"      "tool_call"   "tool_output"
#> [6] "document"   
#> 
#> $confidence
#> NULL
#> 
#> attr(,"class")
#> [1] "shieldr_rule"
rule_pii_email()
#> $id
#> [1] "llm02.pii.email"
#> 
#> $pattern
#> [1] "\\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Za-z]{2,}\\b"
#> 
#> $fn
#> NULL
#> 
#> $owasp
#> [1] "llm02"
#> 
#> $severity
#> [1] "medium"
#> 
#> $action
#> [1] "redact"
#> 
#> $description
#> [1] "Email address."
#> 
#> $stages
#> [1] "prompt"      "context"     "output"      "tool_call"   "tool_output"
#> [6] "document"   
#> 
#> $confidence
#> NULL
#> 
#> attr(,"class")
#> [1] "shieldr_rule"