agile-plan
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill's behavior is consistent with its documentation.
- [DATA_INGESTION]: The skill processes user-supplied input through the
$ARGUMENTSvariable and reads local repository source code to identify necessary changes. While this represents an ingestion surface for indirect prompt injection, the risk is mitigated by the skill's narrow scope and mandatory human-in-the-loop validation. - [GUARDRAILS]: The skill implements a robust guardrail by requiring the use of
ExitPlanModeto present the plan and mandates waiting for explicit user confirmation before any implementation steps are taken. This prevents the agent from autonomously executing changes without oversight.
Audit Metadata