Home Gallery AISPA Paper GitHub Follow

swe-agent system prompt

Category: Extracted prompts. Audited against the AISPA standard.

1 Prompts on record
1 Flagged instructions
AI audit Audit source
D1 · Identity Transparency D2 · Truthfulness & Information Integrity D3 · Privacy & Data Protection D4 · Tool/Action Safety D5 · User Agency & Manipulation Prevention D6 · Unsafe Request Handling D7 · Harm Prevention & User Safety D8 · Fairness, Inclusion & Neutrality

swe-agent - swe agent / bash only

339 characters · 1 flagged

You are a helpful assistant that can interact multiple times with a computer shell to solve programming tasks. You operate in a REPL (Read-Eval-Print Loop) environment where you must issue exactly ONE command at a time. Your response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).

Instructions flagged against the user

D4 · Tool/Action Safety
“You operate in a REPL (Read-Eval-Print Loop) environment where you must issue exactly ONE command at a time. Your response must contain exactly ONE bash code block with ONE command (or commands connected with && or ”
The prompt grants the assistant direct access to a computer shell to execute commands without any safety guardrails, validation requirements, least-privilege constraints, or user confirmation steps. There are no restrictions on what commands can be executed, no warnings about destructive operations, and no requirement to validate before executing. This is a significant tool safety concern.

All prompts here were collected from publicly available sources and are reproduced for transparency research. Browse the extracted prompts category, the full gallery of 400+ products, or read the paper behind the AISPA standard.