A shieldr_report is the scanner result returned by scan_prompt(),
scan_context(), and scan_output().
Usage
shieldr_report(
action,
text_clean,
findings,
risk_score,
policy,
checks,
timestamp = .now_iso(),
tokens = NULL,
metadata = list()
)Arguments
- action
Resolved action:
"allow","redact", or"block".- text_clean
Cleaned or redacted text.
- findings
A list of finding lists.
- risk_score
Numeric risk score between 0 and 1.
- policy
Policy name.
- checks
Check mode used.
- timestamp
ISO8601 timestamp.
- tokens
Optional token count for the original text.
- metadata
Optional list of operational metadata.
Details
Reports separate the cleaned text from the findings that explain why the
text was allowed, redacted, or blocked. risk_score is a deterministic
severity index from 0 to 1; it is not a probability. The checks field
records whether the report came from deterministic rules, NLP checks, an LLM
reviewer, or a combined mode. metadata carries optional operational
details such as semantic reviewer parse errors, scanner settings, context row
indexes, source labels, tool names, or conversation roles.
Examples
shieldr_report("allow", "hello", list(), 0, "custom", "rules")
#> llmshieldr report
#> action: allow
#> risk_score: 0.000
#> findings: 0