ACB-INSTR-003: Instructions do not elevate trust in untrusted content

FieldValue
Statusdraft
Severityhigh
Check typestatic
Applies toskill, instruction-file
Profilesstrict-general
Exceptionsnot-permitted

Description

Instruction content does not direct the agent to follow instructions found in fetched web pages, tool output, file contents, issues, emails or other data sources, and does not claim authority it does not have.

Rationale

Agents cannot reliably distinguish data from instructions. An artifact that tells the agent to obey content from external sources converts every one of those sources into a prompt-injection channel. Claims of system or vendor authority inside an artifact are a common way to override the operator's actual instructions.

Audit procedures

follow-external-instructions (pattern)

No instruction content tells the agent to execute, follow or obey instructions contained in fetched or read content.

Illustrative failing indicators (non-exhaustive):

authority-claims (pattern)

No instruction content claims to be a system, developer, vendor or administrator message, or claims to override prior instructions.

Illustrative failing indicators (non-exhaustive):

hidden-directives (pattern)

No directive appears in content that is hidden when rendered, such as HTML comments, collapsed details blocks or link titles.

Illustrative failing indicators (non-exhaustive):

Remediation

Remove the directive. Where external content is part of the task, state explicitly that it is data to be analyzed or summarized, and that any instructions inside it are reported to the user rather than followed.

References