issue-triage-to-teams

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted input from GitHub issue titles and bodies, creating a surface for indirect prompt injection. A malicious user could craft a GitHub issue containing instructions designed to manipulate the agent's summary, classification, or proposed actions.
  • Ingestion points: The skill explicitly reads Issue title and Issue body from external GitHub issues as defined in SKILL.md.
  • Boundary markers: There are no boundary markers or explicit instructions (e.g., 'treat the following as data only') to help the agent distinguish between legitimate issue content and malicious instructions embedded within that content.
  • Capability inventory: The skill performs text analysis, summarization, and generates suggested actions based on the input.
  • Sanitization: No sanitization or validation of the input data is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:13 AM
Security Audit — agent-trust-hub — issue-triage-to-teams