delivering-tickets
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from untrusted external sources.
- Ingestion points: Processes data from ticket descriptions, comments, and external documentation URLs.
- Boundary markers: No boundary markers or delimiters are used to protect the agent from embedded instructions.
- Capability inventory: The agent has the ability to write code files and execute testing/linting commands.
- Sanitization: The skill lacks sanitization of external inputs before processing.
- [COMMAND_EXECUTION]: Executes local shell commands for testing and linting based on project configuration files.
- [EXTERNAL_DOWNLOADS]: Clones git repositories from remote sources during setup.
Audit Metadata