qe-defect-intelligence
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources, which could contain malicious instructions aimed at influencing the agent's behavior.
- Ingestion points: The skill ingests data from Git PR changes (via
aqe defect predict --changes), Jira issue descriptions and comments (viasyncWithTracker), and test result logs. - Boundary markers: There are no documented boundary markers or delimiters specified to isolate untrusted data from the agent's instructions, nor are there instructions to ignore embedded prompts in the analyzed content.
- Capability inventory: The skill coordinates multiple specialized agents and has the ability to modify external state by creating tasks and updating labels in the Jira issue tracker.
- Sanitization: The analysis of the skill's scripts and documentation reveals no explicit logic for sanitizing or filtering input retrieved from code repositories or issue trackers before it is processed by the AI agents.
Audit Metadata