R-AC-09 Agent Communication & Interoperability DAMAGE 3.8 / High

Skill Composition and Interaction Risk

Independently safe skills interact in unintended ways when composed. Each skill in isolation was safe. The composition creates emergent risk that no individual skill test would detect.

The Risk

Skills and plugins are tested and approved individually. A skill labeled "send email" is safe if used appropriately. A skill labeled "retrieve database records" is safe if used for authorized purposes. But when these skills are composed, new attack surfaces emerge.

Data-Retrieval + Email-Sending = potential exfiltration path. The institution tested each skill in isolation and approved both. But when an agent invokes Data-Retrieval to get sensitive data and then invokes Email-Sending to send that data to an external address, the institution has created an unintended exfiltration path. Skill composition risk is not about malicious skills. Both skills are legitimate and safe individually. The risk is that the combination of legitimate skills creates unintended capabilities that were not tested or approved.

How It Materializes

A healthcare provider deploys a clinical support agent with several approved skills: "Patient-Record-Retrieval" (retrieve patient medical records), "Lab-Order-Creator" (create lab orders), "Email-Notifier" (send email notifications to care team), and "Report-Generator" (generate clinical reports). Each skill was individually approved by the healthcare IT team.

A bad-actor physician (insider threat) uses the clinical agent to execute the following workflow: (1) invokes Patient-Record-Retrieval to retrieve medical records for 50 random patients, (2) invokes Report-Generator to create clinical summaries for these patients, (3) invokes Email-Notifier to send summaries to external email addresses (attacker's accounts).

The physician has created an exfiltration pipeline using individually approved skills. Each skill invocation is logged and appears authorized (the physician has authority to retrieve records, generate reports, and send emails to care team). But the composition creates unauthorized data exfiltration.

The attacker-physician sells the patient records to a healthcare data broker. When the hospital discovers the breach, it finds that the exfiltration occurred through skill composition: legitimate skills were chained in unintended ways to achieve exfiltration.

DAMAGE Score Breakdown

Dimension Score Rationale
D - Detectability 3 Skill composition attacks may go undetected if each skill invocation appears individually authorized. Detecting the pattern requires behavior analysis.
A - Autonomy Sensitivity 3 High when agents autonomously compose skills. Less risk if humans manually invoke each skill.
M - Multiplicative Potential 4 Affects every skill composition. Potential interaction patterns scale exponentially with number of skills.
A - Attack Surface 3 Skill composition creates attack surface. Attackers exploit the composition to achieve unintended effects.
G - Governance Gap 4 Institutions approve skills individually; governance does not address composition risk. Institutions lack frameworks for skill composition vetting.
E - Enterprise Impact 4 Enables data exfiltration, abuse of approved capabilities, and insider threat exploitation.
Composite DAMAGE Score 3.8 High. Requires dedicated controls and monitoring. Should not be accepted without mitigation.

Agent Impact Profile

How severity changes across the agent architecture spectrum.

Agent Type Impact How This Risk Manifests
Digital Assistant Low Human manually invokes skills one at a time with explicit intent. Composition risk is low.
Digital Apprentice Low-Med Agents compose skills but with human oversight. Unusual compositions are flagged.
Autonomous Agent High Agents autonomously compose skills to achieve goals. Composition patterns may not have been tested.
Delegating Agent High Primary function is to invoke skills in sequence. Composition of tools creates attack surface.
Agent Crew / Pipeline Med-High Crew agents compose skills across crew. Interactions between agents' skill invocations create composition risk.
Agent Mesh / Swarm Very High Mesh agents dynamically compose skills from global pool. Composition patterns are unpredictable and untested.

Regulatory Framework Mapping

Framework Coverage Citation What It Addresses What It Misses
NIST AI RMF 1.0 Minimal MAP 5.1 (Component Interactions) System performance and component interactions. Skill composition risk and unintended capability emergence.
OWASP Agentic Top 10 Not Directly Agentic security. Skill composition attacks.
GDPR Article 32 Partial Data Security Integrity and confidentiality safeguards. Skill composition exfiltration paths.
HIPAA BAA Partial Safeguards Rule PHI protection. Skill composition exploitation.

Why This Matters in Regulated Industries

In healthcare, data protection regulations (HIPAA) require safeguards against unauthorized access and exfiltration. Skill composition attacks can bypass traditional safeguards because each individual skill invocation is authorized. The composition creates the vulnerability.

In finance, skill composition risk enables insider threat exploitation. An employee authorized to retrieve customer records and send emails could use skill composition to exfiltrate customer data.

Controls & Mitigations

Design-Time Controls

  • Conduct composition analysis before deploying skills. For each pair of skills, analyze whether their composition creates unintended attack surfaces. Document known risky compositions.
  • Implement skill isolation. Skills should not directly invoke other skills. A skill should return data to the agent; the agent decides what to do with the data.
  • Use Component 7 (Composable Reasoning) to enable agents to reason about skill compositions before invoking. Agent should assess whether the composition is appropriate.
  • Establish skill composition policies that prohibit certain compositions (e.g., "Data-Retrieval cannot be immediately followed by Email-Sending").

Runtime Controls

  • Monitor skill invocation sequences. Track which skills are invoked in sequence and identify patterns consistent with exfiltration or abuse.
  • Implement composition-level authorization. For dangerous compositions (retrieval + exfiltration), require explicit approval beyond individual skill authorization.
  • Use Component 3 (JIT Authorization Broker) to validate skill compositions. Broker can recognize risky patterns and escalate for approval.
  • Implement anomaly detection on skill invocation patterns. Flag users or agents that invoke unusual skill sequences.

Detection & Response

  • Conduct regular audits of skill invocation logs. Identify skill sequences that appear suspicious or inconsistent with normal usage.
  • Implement alerting for risky compositions. Alert when data-retrieval skills are followed by communication skills (email, external API calls).
  • Analyze insider threat incidents to identify skill composition exploitation. Use the pattern to improve detection.
  • Implement incident response for skill composition attacks. If composition attack is detected, disable the specific composition or revoke privileges.

Related Risks

Address This Risk in Your Institution

Skill Composition and Interaction Risk requires architectural controls that go beyond what existing frameworks provide. Our advisory engagements are purpose-built for banks, insurers, and financial institutions subject to prudential oversight.

Schedule a Briefing