planner-agent
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes source code and uses the output to perform actions in Jira.
- Ingestion points: The planner-agent reads project code to generate implementation steps (SKILL.md).
- Boundary markers: The skill does not include specific boundary markers or instructions to ignore instructions embedded in the code it reads.
- Capability inventory: The skill set has the ability to read the file system and interact with the Jira API to create and transition tasks (jira/SKILL.md).
- Sanitization: There is no evidence of sanitization for the inputs retrieved from the project environment before they are sent to Jira.
Audit Metadata