P2: Embedded Scaffold #

A long prompt is embedded directly in Python source. It may be easier to maintain as a concise instruction or a separately versioned file.

P2INFO–LOWLintLang 0.8.0

Applies to: Recognized Python prompt literals. Manual repair; no automatic fix for this example.

What triggers it #

Recognized prompt literals longer than 200 and at most 500 characters emit INFO; those longer than 500 emit LOW. This is maintenance advice, not a claim of runtime failure.

How to repair it #

Remove repetition while preserving the task and output contract. Externalize frequently edited prompts when that improves your workflow, and scan the external file too.

Reproduce the finding #

Use uv and Python 3.10+, plus curl. Run the examples in a scratch directory.

Download the finding example.

system_prompt = 'You are an invoice reviewer. Compare each line item total with quantity times unit price. Sum the line totals and compare them with the invoice total. Return each discrepancy as JSON with its line number, expected amount, and stated amount. Use only the supplied invoice.'

curl -fsS https://lintlang.ai/examples/rules/p2-bad.py -o p2-bad.py
uvx --from lintlang==0.8.0 lintlang scan p2-bad.py --format json

Expected with 0.8.0: the JSON report includes P2, severity INFO. The improved literal stays above the extraction minimum and preserves the invoice checks and output fields, while reducing its length below the P2 threshold.

Improved example #

Download the improved example.

system_prompt = 'You are an invoice reviewer. Check quantity × unit price and summed totals using only this invoice. Return discrepancies as JSON: line number, expected amount, stated amount.'

curl -fsS https://lintlang.ai/examples/rules/p2-improved.py -o p2-improved.py
uvx --from lintlang==0.8.0 lintlang scan p2-improved.py --format json

Expected with 0.8.0: P2 is absent. Other diagnostics may still appear; this repair targets the rule above.

Both commands use advisory mode: a finding does not itself make the command fail. This example is advisory: LOW and INFO findings do not fail either --fail-on threshold. See outputs and exit codes.

Detection details #

Released P2 detection contract and scope

Python source is parsed, not imported or executed. The extractor recognizes string literals of at least 50 characters with a supported prompt signal. F-string literal portions are retained with {...} placeholders for expressions; runtime interpolation and data flow are not evaluated. Prompt candidates are deduplicated by their first 200 characters, so distinct strings with the same prefix can collapse to one candidate. Python syntax errors produce ERROR.

Only H2, H4, H5, and H6 run on extracted prompts. Literal Python tool definitions provide a separate declared surface on which H1 and H3 run; H7 does not run in Python extraction mode. Selecting a family for which a Python input provides no supported surface is not proof that the check passed. P1/P2 still run independently of that selection.

P1: Uncalibrated Threshold. Inspects supported nonzero numeric assignments to threshold/confidence-like names, excluding recognized counters. No recognized nearby calibration comment produces MEDIUM; a recognized comment containing uncertainty markers can produce LOW. This tests a documented justification signal, not whether the threshold was actually calibrated or is correct.
A string is extracted as a prompt when the code uses it as one: it is bound to a prompt-like name, keyword argument or message-dict key (prompt, system, instructions, template, content, ...), or it addresses a model ("You are", "your task"), or it matches three or more prompt signals. Docstrings, bare string statements, and text passed to logging, argparse/click help, or an exception are never prompts.
Tool definitions written as literals are read: a call or dict literal with a literal name, a schema keyword (inputSchema, input_schema, parameters, parameters_json_schema, args_schema) and a literal or absent description — the way Python MCP servers declare Tool(name=..., description=..., inputSchema=...). H1 and H3 run on them, with the call's line. Tools declared by decorator and docstring, or with a computed description, are not read. A dynamic or non-object schema expression is not evaluated: the literal name and description remain inspected, while the schema is excluded from tools_with_schema and named under not_inspected.
P2: Embedded Scaffold. An extracted prompt longer than 500 characters produces LOW; one longer than 200 and at most 500 produces INFO. It suggests reviewing whether the prompt should be externalized, not that embedded prompts necessarily cause runtime failures.

A Python file with no recognized prompt may still have P1 findings. A clean scan cannot establish that dynamically assembled prompts or every pipeline were inspected. Python decoding currently ignores invalid UTF-8 bytes; ordinary text/configuration loading uses strict UTF-8. Neither path executes source code.

All scan rules · Quickstart · Separate preflight checks.