flow-ticket

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources such as ticket connectors, CLI outputs, and attachments.
  • Ingestion points: According to SKILL.md, the skill reads descriptions and attachments from ticket sources to populate local tracking files.
  • Boundary markers: The instructions lack explicit delimiters or "ignore instructions" warnings to prevent the agent from accidentally executing commands embedded within the retrieved ticket text.
  • Capability inventory: The skill has the capability to write files to the project root (creating .task/ and assets/ directories), modify .gitignore, and read internal configuration files like AGENTS.md and CLAUDE.md.
  • Sanitization: No sanitization or validation logic is defined for the external content before it is processed or stored locally.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 08:04 AM
Security Audit — agent-trust-hub — flow-ticket