aile-writing-plans
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill's file system operations and tool interactions are consistent with its primary purpose of managing development plans.
- [PROMPT_INJECTION]: The skill processes untrusted external data, which creates a surface for indirect prompt injection.
- Ingestion points: Jira story descriptions and UI documentation read during the initialization and boundary confirmation steps.
- Boundary markers: Absent; the prompt does not specify the use of clear delimiters or instructions to ignore embedded commands within the ingested content.
- Capability inventory: Access to tools for creating and updating Jira issues, writing to the local filesystem, and performing git commit operations.
- Sanitization: No explicit sanitization or filtering of the external Jira content is mentioned in the instructions.
Audit Metadata