deal-team-summary

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data originating from external sources (diligence findings and deal context) without explicit sanitization. \n
  • Ingestion points: diligence-issue-extraction output and deal-context.md. \n
  • Boundary markers: The instructions lack specific delimiters or warnings to ignore potential instructions embedded within findings. \n
  • Capability inventory: The agent has read/write access to the local file system (specifically the plugin configuration and matter directories) to perform its task. \n
  • Sanitization: No validation or filtering of input data is specified in the instructions. \n- [NO_CODE]: This skill consists entirely of natural language instructions and does not include any accompanying scripts or executable files, limiting its potential for traditional malware behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — deal-team-summary