security-report

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted data from security scan results and Software Bill of Materials (SBOMs).
  • Ingestion points: External data enters the context via harness_list and harness_get tools in SKILL.md (Steps 1 through 7).
  • Boundary markers: The instructions lack delimiters or isolation markers to separate external data from the agent's instructions.
  • Capability inventory: The skill includes tools to create, approve, or revoke security exemptions (harness_create, harness_execute), which could be targets for malicious instructions embedded in scan data.
  • Sanitization: No explicit sanitization or content validation steps are defined for the data retrieved from the Harness API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 06:18 AM
Security Audit — agent-trust-hub — security-report