skills/lukastk/sesh/do-tickets/Gen Agent Trust Hub

do-tickets

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface because it instructs the agent to ingest and follow instructions stored in external ticket prompts.
  • Ingestion points: Data enters the agent's context through the sesh ticket get --id <id> --field prompt command in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or warnings to treat the retrieved ticket content as untrusted or to ignore embedded instructions that might contradict safety guidelines.
  • Capability inventory: The agent is empowered to execute shell commands (sesh), manage files (via @blob expansion), and perform work tasks (referenced by commit-sha) based on the content of these external tickets.
  • Sanitization: There is no mention of filtering or sanitizing the ticket prompt before it is delivered to or read by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 09:26 AM
Security Audit — agent-trust-hub — do-tickets