zentao-release

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external release data from a ZenTao instance, which could potentially contain malicious instructions embedded in fields like release names or descriptions.
  • Ingestion points: Data is ingested via zentao-cli release list and zentao-cli release get (referenced in SKILL.md and multiple reference files).
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are defined to separate ingested data from agent instructions.
  • Capability inventory: The skill possesses the capability to modify the ZenTao environment through zentao-cli release create, update, and delete commands.
  • Sanitization: The instructions do not specify any sanitization, validation, or escaping of the content retrieved from the CLI before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:26 AM
Security Audit — agent-trust-hub — zentao-release