okr-native
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with
https://open.feishu.cn, the official API endpoint for the Feishu/Lark enterprise collaboration platform. These requests are used to fetch OKR periods, user OKR lists, and details. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes user-generated content (OKR titles and descriptions) from an external API and presents it to the agent.
- Ingestion points: Data enters through the
_lark_apifunction inrun.pyfrom endpoints such as/okr/v1/users/{user_id}/okrsand/okr/v1/okrs/batch_get. - Boundary markers: No explicit delimiters or instructions are used to distinguish the retrieved data from system instructions.
- Capability inventory: The script has network access via
urlliband filesystem access through environment variable loading, but it does not execute arbitrary shell commands or subprocesses. - Sanitization: No sanitization or filtering of the retrieved OKR content is performed before it is passed to the agent.
Audit Metadata