skills/oldwinter/skills/to-issues/Gen Agent Trust Hub

to-issues

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions. The skill operates within expected bounds for a project management assistant.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted data from issue comments and project specifications. However, the risk is mitigated by a mandatory user review phase before any external actions are performed.
  • Ingestion points: Plan/spec context and external issue tracker comments (SKILL.md).
  • Boundary markers: Not explicitly used to delimit data from instructions.
  • Capability inventory: Reading from and writing to project issue trackers.
  • Sanitization: No explicit sanitization or filtering of input content identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 12:29 AM
Security Audit — agent-trust-hub — to-issues