agile-planning
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill accesses a local template file at
~/.agents/templates/planning.md. This is a standard configuration path for the agent and does not involve sensitive credentials or private user data. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from project backlogs, epics, and retrospective notes to generate sprint plans. This represents a potential surface for indirect prompt injection if those sources contain malicious instructions.
- Ingestion points: Reads epic stories, retro actions, and backlog items (SKILL.md).
- Boundary markers: No specific delimiters are defined to separate untrusted data from system instructions.
- Capability inventory: The skill has the ability to write files to the
planning/directory (SKILL.md). - Sanitization: No explicit sanitization or validation of the external content is performed before processing.
Audit Metadata