aisecurity.llc
The Agentic Surface Emergence
Prompt-injection, function-calling, and tool-calling security signals are still under 0.3% of all postings, but rising quickly.
Early but accelerating risk surface
What this finding measures
Internal / Teaser Only
Prompt-injection, function-calling, and tool-calling security signals are still under 0.3% of all postings, but rising quickly.
Based on analyzed job-description signals, not proof of any individual company’s internal security maturity.
Agentic-surface concentration
0.24%
Chart targets
- chart_agentic_surface_map
- chart_survey_practitioner_observed_issues
Active filters: period=all, industry=all, seniority=all
Evidence charts
Current chart outputs for this finding
Agentic Security
Agentic Attack Surface Map
export.v_public_top_attack_surfaces_export
Source: export.v_public_top_attack_surfaces_export
Based on analyzed job-description signals, not proof of any individual company's internal security maturity.
Chart ID: chart_agentic_surface_map
Source: export.v_public_top_attack_surfaces_export
AI Security Issues Observed in Production (Practitioners)
No rows matched current filters or export rows are not populated yet.
Recommended actions
What leaders should do next
Treat delegated-action controls as near-term hiring priority.
Add agentic attack-surface scenarios to interviews.
Instrument authorization and rollback evidence for agent workflows.
Browse the full citation library for supporting research and source quotes.
Evidence library →